SlideShare a Scribd company logo
1 of 62
Download to read offline
Toward Eliminating
Hallucinations
F. Sovrano, K. Ashley, A. Bacchelli
GPT-based Explanatory AI for
Intelligent Textbooks and
Documentation
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
2
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
3
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
4
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
5
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
6
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
7
Outline
The contents of this presentation will be
organised as follows:
• Introduction
• Background
• Proposed Approach
• Experiment
• Discussion
• Conclusions
8
Problem and Motivation
• Problem: Too much static information. How
to explain it?
• Advancements in NLP, such as models like
ChatGPT, can provide dynamic explanations.
• However, these models introduce challenges
like hallucinations.
• Memory constraints are another challenge
associated with using NLP models for
dynamic explanations.
9
Problem and Motivation
• Problem: Too much static information. How
to explain it?
• Advancements in NLP, such as models like
ChatGPT, can provide dynamic explanations.
• However, these models introduce challenges
like hallucinations.
• Memory constraints are another challenge
associated with using ChatGPT.
10
Problem and Motivation
• Problem: Too much static information. How
to explain it?
• Advancements in NLP, such as models like
ChatGPT, can provide dynamic explanations.
• However, these models introduce challenges
like hallucinations.
• Memory constraints are another challenge
associated with using ChatGPT.
11
Problem and Motivation
• Problem: Too much static information. How
to explain it?
• Advancements in NLP, such as models like
ChatGPT, can provide dynamic explanations.
• However, these models introduce challenges
like hallucinations.
• Memory constraints are another challenge
associated with using ChatGPT.
12
Proposal: ExplanatoryGPT
• ExplanatoryGPT is a combination of ChatGPT with
answer retrieval algorithms.
• It’s designed to address memory constraints and
hallucinations
• ExplanatoryGPT integrates question generation
and answer retrieval algorithms. It’s based on
Achinstein's theory of explanations to address the
abovementioned issues.
• Hallucination: the generation of content that does
not maintain fidelity to a given context or source.
13
Proposal: ExplanatoryGPT
• ExplanatoryGPT is a combination of ChatGPT with
answer retrieval algorithms.
• It’s designed to address memory constraints and
hallucinations
• ExplanatoryGPT integrates question generation
and answer retrieval algorithms. It’s based on
Achinstein's theory of explanations to address the
abovementioned issues.
• Hallucination: the generation of content that does
not maintain fidelity to a given context or source.
14
Proposal: ExplanatoryGPT
• ExplanatoryGPT is a combination of ChatGPT with
answer retrieval algorithms.
• It’s designed to address memory constraints and
hallucinations
• ExplanatoryGPT integrates question generation
and answer retrieval algorithms. It’s based on
Achinstein's theory of explanations to address the
abovementioned issues.
• Hallucination: the generation of content that does
not maintain fidelity to a given context or source.
15
Proposal: ExplanatoryGPT
• ExplanatoryGPT is a combination of ChatGPT with
answer retrieval algorithms.
• It’s designed to address memory constraints and
hallucinations
• ExplanatoryGPT integrates question generation
and answer retrieval algorithms. It’s based on
Achinstein's theory of explanations to address the
abovementioned issues.
• Hallucination: the generation of content that does
not maintain fidelity to a given context or source.
16
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
– Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
– It’s the difference between answering questions
and explaining.
• Example: “How are you?”
– “Alright”: not an explanation.
– “I’m good, because I just successfully defended my
PhD, etc.”
17
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
• Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
• It’s the difference between answering questions
and explaining.
• Example: “How are you?”
• “Alright”: not an explanation.
• “I’m good, because I just successfully defended my
PhD, etc.”
18
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
• Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
• It’s the difference between answering questions
and explaining.
• Example: “How are you?”
– “Alright”: not an explanation.
– “I’m good, because I just successfully defended my
PhD, etc.”
19
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
• Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
• It’s the difference between answering questions
and explaining.
• Example: “How are you?”
• “Alright”: not an explanation.
• “I’m good, because I just successfully defended my
PhD, etc.”
20
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
• Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
• It’s the difference between answering questions
and explaining.
• Example: “How are you?”
• “Alright”: not an explanation.
• “I’m good, because I just successfully defended my
PhD, etc.”
21
Background
• Achinstein: Explaining is an illocutionary act with
the intention to provide new understandings to the
explainee by answering questions.
• Illocution (in explanations):
• Equivalent to pertinently anticipating implicit
(archetypal) questions, e.g., Why? What for? How?
When? etc.
• It’s the difference between answering questions
and explaining.
• Example: “How are you?”
• “Alright”: not an explanation.
• “I’m good, because I just successfully defended my
PhD, etc.”
22
Why Achinstein’s Theory?
• This definition of illocution is computer-friendly.
We can use linguistic theories to define and
generate implicit archetypal questions and AI can
help us estimate how pertinently they are
answered.
• Our tech: textbook or documentation
information is extracted and organised by
question-answering algorithms.
• ChatGPT is used to refine the retrieved
information, improving readability, coherence,
and cohesion.
23
Why Achinstein’s Theory?
• This definition of illocution is computer-friendly.
We can use linguistic theories to define and
generate implicit archetypal questions and AI can
help us estimate how pertinently they are
answered.
• Our tech: answer retrieval algorithms which can
extract information out of textbooks or
documentation.
• ChatGPT is used to refine the retrieved
information, improving readability, coherence,
and cohesion.
24
Why Achinstein’s Theory?
• This definition of illocution is computer-friendly.
We can use linguistic theories to define and
generate implicit archetypal questions and AI can
help us estimate how pertinently they are
answered.
• Our tech: answer retrieval algorithms which can
extract information out of textbooks or
documentation.
• We use ChatGPT to refine the retrieved
information, improving readability, coherence,
and cohesion.
25
Example: Q&A for Explaining
26
The Technology in a Nutshell
27
The Prompt
28
ExplanatoryGPT’s
prompt
Applications
We applied ExplanatoryGPT to
• a law textbook,
• Software documentation of:
• a credit approval system,
• a heart disease predictor.
29
Applications
We applied ExplanatoryGPT to
• a law textbook,
• software documentation of
• a credit approval system,
• a heart disease predictor.
30
Applications
We applied ExplanatoryGPT to
• a law textbook,
• software documentation of
‣ a credit approval system,
• a heart disease predictor.
31
Applications
We applied ExplanatoryGPT to
• a law textbook,
• software documentation of
‣ a credit approval system,
‣ a heart disease predictor.
32
Proof of Concept
33
Example of interface!
Proof of Concept
34
An AI decides to deny a loan
Proof of Concept
35
An XAI explains why
Proof of Concept
36
John can access external
documentation/explanations
Proof of Concept
37
An overview is opened
38
Connected to other overviews
Proof of Concept
39
Intelligent annotation:
not all words are
underlined
Proof of Concept
40
Illocution is used
to anchor
pertinent contents
Credit Approval System
41
ChatGPT re-writes and
amalgamates the
retrieved answers
Proof of Concept
42
There is also room for
user-defined questions
Proof of Concept
Small Experiment
• We compared ChatGPT with
ExplanatoryGPT on the law textbook.
43
Small Experiment
• We compared ChatGPT with
ExplanatoryGPT on the law textbook.
44
ChatGPT’s prompt
Small Experiment
• We compared ChatGPT with
ExplanatoryGPT on the law textbook.
45
ExplanatoryGPT’s
prompt
Results
46
ExplanatoryGPT knows
the context better
Results
47
ExplanatoryGPT is
less hallucinated
Results
48
ExplanatoryGPT is
more precise
Discussion
• ChatGPT could be fed with the whole
explanation context necessary for
generating appropriate responses.
• But without a filtering mechanism we
would hit ChatGPT's memory constraints.
• ChatGPT cannot process more than a few
pages.
• Our YAI doesn’t have this problem. We use
answer retrieval to generate accurate and
context-specific outputs.
49
Discussion
• ChatGPT could be fed with the whole
explanation context necessary for
generating appropriate responses.
• But without a filtering mechanism we
would hit ChatGPT's memory constraints.
• ChatGPT cannot process more than a few
pages.
• Our YAI doesn’t have this problem. We use
answer retrieval to generate accurate and
context-specific outputs.
50
Discussion
• ChatGPT could be fed with the whole
explanation context necessary for
generating appropriate responses.
• But without a filtering mechanism we
would hit ChatGPT's memory constraints.
• ChatGPT cannot process more than a few
pages.
• Our YAI doesn’t have this problem. We use
answer retrieval to generate accurate and
context-specific outputs.
51
Discussion
• ChatGPT could be fed with the whole
explanation context necessary for
generating appropriate responses.
• But without a filtering mechanism we
would hit ChatGPT's memory constraints.
• ChatGPT cannot process more than a few
pages.
• Our YAI doesn’t have this problem. We use
answer retrieval to generate accurate and
context-specific outputs.
52
More Discussion
• The answer retrieval mechanism is
used for macro-planning: the
selection of information.
• ChatGPT is then used for surface
realisation.
• Thus, ExplanatoryGPT can provide
specific and context-aware
explanations, avoiding broad or
incorrect responses.
53
More Discussion
• The answer retrieval mechanism is
used for macro-planning: the
selection of information.
• ChatGPT is then used for surface
realisation.
• Thus, ExplanatoryGPT can provide
specific and context-aware
explanations, avoiding broad or
incorrect responses.
54
More Discussion
• The answer retrieval mechanism is
used for macro-planning: the
selection of information.
• ChatGPT is then used for surface
realisation.
• Thus, ExplanatoryGPT can provide
specific and context-aware
explanations, avoiding broad or
incorrect responses.
55
Conclusions
• Answer retrieval and ChatGPT complement each other.
• This methodology has potential for improving
explanations in intelligent textbooks and
documentation.
• Future research:
– experiments to verify whether ExplanatoryGPT
helps enhancing educational materials and
software documentation;
– experiments to verify whether ExplanatoryGPT is
better than ChatGPT.
56
Conclusions
• Answer retrieval and ChatGPT complement each other.
• This methodology has potential for improving
explanations in intelligent textbooks and
documentation.
• Future research:
– experiments to verify whether ExplanatoryGPT
helps enhancing educational materials and
software documentation;
– experiments to verify whether ExplanatoryGPT is
better than ChatGPT.
57
Conclusions
• Answer retrieval and ChatGPT complement each other.
• This methodology has potential for improving
explanations in intelligent textbooks and
documentation.
• Future research:
• experiments to verify whether ExplanatoryGPT
helps enhancing educational materials and software
documentation;
• experiments to verify whether ExplanatoryGPT is
better than ChatGPT.
58
Conclusions
• Answer retrieval and ChatGPT complement each other.
• This methodology has potential for improving
explanations in intelligent textbooks and
documentation.
• Future research:
• experiments to verify whether ExplanatoryGPT
helps enhancing educational materials and software
documentation;
• experiments to verify whether ExplanatoryGPT is
better than ChatGPT.
59
Questions?
60
61
Speaker: Francesco Sovrano
Email: francesco.sovrano@uzh.ch

More Related Content

Similar to Toward Eliminating Hallucinations: GPT-based Explanatory AI for Intelligent Textbooks and Documentation

Lab Report Guidelines Title Page Include the lab tit
Lab Report Guidelines   Title Page Include the lab titLab Report Guidelines   Title Page Include the lab tit
Lab Report Guidelines Title Page Include the lab titJospehStull43
 
Answer Direct Interview
Answer    Direct InterviewAnswer    Direct Interview
Answer Direct InterviewPedro Craggett
 
Chapter 3 class version
Chapter 3 class versionChapter 3 class version
Chapter 3 class versionjbnx
 
Handbook for the project paper
Handbook for the project paperHandbook for the project paper
Handbook for the project paperpheysl
 
Research question
Research questionResearch question
Research questionmaeenhsn
 
ERS5900_WEEK 34_SOPRQ.pptx
ERS5900_WEEK 34_SOPRQ.pptxERS5900_WEEK 34_SOPRQ.pptx
ERS5900_WEEK 34_SOPRQ.pptxAsmaAsma278326
 
Presentation2
Presentation2Presentation2
Presentation2cocolatto
 
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...Ahmed Yehia
 
Enhancing Test Questions Using KPUP Format
Enhancing Test Questions Using KPUP FormatEnhancing Test Questions Using KPUP Format
Enhancing Test Questions Using KPUP FormatJoseline Santos
 
03 The scientific method in research.pptx
03 The scientific method in research.pptx03 The scientific method in research.pptx
03 The scientific method in research.pptxssusere05ec21
 
Writing an Argumentative, Research-Based Body Paragraph
Writing an Argumentative, Research-Based Body ParagraphWriting an Argumentative, Research-Based Body Paragraph
Writing an Argumentative, Research-Based Body ParagraphLauren Blackwell
 
A Writer's Algorithm: Papers without (too much) Pain
A Writer's Algorithm: Papers without (too much) PainA Writer's Algorithm: Papers without (too much) Pain
A Writer's Algorithm: Papers without (too much) PainCTSI at UCSF
 
research apptitude
research apptitude research apptitude
research apptitude Garret Raja
 
Lecture 01 & 02 (Research Basics).ppt
Lecture 01 & 02 (Research Basics).pptLecture 01 & 02 (Research Basics).ppt
Lecture 01 & 02 (Research Basics).pptKamiBhutta
 
Why Do Employees Forget?
Why Do Employees Forget?Why Do Employees Forget?
Why Do Employees Forget?Axonify
 
Writing introduction in research report and articles
Writing introduction in research report and articlesWriting introduction in research report and articles
Writing introduction in research report and articlesAchyut Raj Pandey
 
Research method chapter 1
Research method chapter 1Research method chapter 1
Research method chapter 1Abiy Almaw
 

Similar to Toward Eliminating Hallucinations: GPT-based Explanatory AI for Intelligent Textbooks and Documentation (20)

Lab Report Guidelines Title Page Include the lab tit
Lab Report Guidelines   Title Page Include the lab titLab Report Guidelines   Title Page Include the lab tit
Lab Report Guidelines Title Page Include the lab tit
 
Answer Direct Interview
Answer    Direct InterviewAnswer    Direct Interview
Answer Direct Interview
 
odisee.pptx
odisee.pptxodisee.pptx
odisee.pptx
 
Chapter 3 class version
Chapter 3 class versionChapter 3 class version
Chapter 3 class version
 
Handbook for the project paper
Handbook for the project paperHandbook for the project paper
Handbook for the project paper
 
Great Pitches
Great PitchesGreat Pitches
Great Pitches
 
Research question
Research questionResearch question
Research question
 
ERS5900_WEEK 34_SOPRQ.pptx
ERS5900_WEEK 34_SOPRQ.pptxERS5900_WEEK 34_SOPRQ.pptx
ERS5900_WEEK 34_SOPRQ.pptx
 
Presentation2
Presentation2Presentation2
Presentation2
 
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...
Research question and research problem Ahmed Yehia, MD IMMUNOLOGY, BENI-SUEF,...
 
Enhancing Test Questions Using KPUP Format
Enhancing Test Questions Using KPUP FormatEnhancing Test Questions Using KPUP Format
Enhancing Test Questions Using KPUP Format
 
03 The scientific method in research.pptx
03 The scientific method in research.pptx03 The scientific method in research.pptx
03 The scientific method in research.pptx
 
Writing an Argumentative, Research-Based Body Paragraph
Writing an Argumentative, Research-Based Body ParagraphWriting an Argumentative, Research-Based Body Paragraph
Writing an Argumentative, Research-Based Body Paragraph
 
A Writer's Algorithm: Papers without (too much) Pain
A Writer's Algorithm: Papers without (too much) PainA Writer's Algorithm: Papers without (too much) Pain
A Writer's Algorithm: Papers without (too much) Pain
 
research apptitude
research apptitude research apptitude
research apptitude
 
Lecture 01 & 02 (Research Basics).ppt
Lecture 01 & 02 (Research Basics).pptLecture 01 & 02 (Research Basics).ppt
Lecture 01 & 02 (Research Basics).ppt
 
Types of Research
Types of ResearchTypes of Research
Types of Research
 
Why Do Employees Forget?
Why Do Employees Forget?Why Do Employees Forget?
Why Do Employees Forget?
 
Writing introduction in research report and articles
Writing introduction in research report and articlesWriting introduction in research report and articles
Writing introduction in research report and articles
 
Research method chapter 1
Research method chapter 1Research method chapter 1
Research method chapter 1
 

More from Sergey Sosnovsky

Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...
Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...
Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...Sergey Sosnovsky
 
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...Sergey Sosnovsky
 
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...Sergey Sosnovsky
 
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...Sergey Sosnovsky
 
Creating Session Data from eTextbook Event Streams
Creating Session Data from eTextbook Event StreamsCreating Session Data from eTextbook Event Streams
Creating Session Data from eTextbook Event StreamsSergey Sosnovsky
 
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...Sergey Sosnovsky
 
Interactions of reading and assessment activities
Interactions of reading and assessment activitiesInteractions of reading and assessment activities
Interactions of reading and assessment activitiesSergey Sosnovsky
 
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...Sergey Sosnovsky
 
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for Education
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for EducationYAI4Edu: an Explanatory AI to Generate Interactive e-Books for Education
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for EducationSergey Sosnovsky
 
Automatic Question Generation for Evidence-based Online Courseware Engineering
Automatic Question Generation for Evidence-based Online Courseware EngineeringAutomatic Question Generation for Evidence-based Online Courseware Engineering
Automatic Question Generation for Evidence-based Online Courseware EngineeringSergey Sosnovsky
 
Reading Comprehension Quiz Generation using Generative Pre-trained Transformers
Reading Comprehension Quiz Generation using Generative Pre-trained TransformersReading Comprehension Quiz Generation using Generative Pre-trained Transformers
Reading Comprehension Quiz Generation using Generative Pre-trained TransformersSergey Sosnovsky
 
Mathematical Language Processing via Tree Embeddings
Mathematical Language Processing via Tree EmbeddingsMathematical Language Processing via Tree Embeddings
Mathematical Language Processing via Tree EmbeddingsSergey Sosnovsky
 
Contextual Definition Generation
Contextual Definition GenerationContextual Definition Generation
Contextual Definition GenerationSergey Sosnovsky
 
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...Sergey Sosnovsky
 
Generation of Assessment Questions from Textbooks Enriched with Knowledge Models
Generation of Assessment Questions from Textbooks Enriched with Knowledge ModelsGeneration of Assessment Questions from Textbooks Enriched with Knowledge Models
Generation of Assessment Questions from Textbooks Enriched with Knowledge ModelsSergey Sosnovsky
 
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...Using Semantics of Textbook Highlights to Predict Student Comprehension and K...
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...Sergey Sosnovsky
 
Dental TutorBot: Exploitation of Dental Textbooks for Automated Learning
Dental TutorBot: Exploitation of Dental Textbooks for Automated LearningDental TutorBot: Exploitation of Dental Textbooks for Automated Learning
Dental TutorBot: Exploitation of Dental Textbooks for Automated LearningSergey Sosnovsky
 
Using Programmed Instruction to Help Students Engage with eTextbook Content
Using Programmed Instruction to Help Students Engage with eTextbook Content Using Programmed Instruction to Help Students Engage with eTextbook Content
Using Programmed Instruction to Help Students Engage with eTextbook Content Sergey Sosnovsky
 
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...Sergey Sosnovsky
 

More from Sergey Sosnovsky (20)

Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...
Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...
Harnessing Textbooks for High-Quality Labeled Data: An Approach to Automatic ...
 
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...
Layout- and Activity-based Textbook Modeling for Automatic PDF Textbook Extra...
 
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...
Exploring the Content Ecosystem of the First Open-source Adaptive Tutor and i...
 
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...
Advancing Intelligent Textbooks with Automatically Generated Practice: A Larg...
 
Creating Session Data from eTextbook Event Streams
Creating Session Data from eTextbook Event StreamsCreating Session Data from eTextbook Event Streams
Creating Session Data from eTextbook Event Streams
 
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...
Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions ...
 
Interactions of reading and assessment activities
Interactions of reading and assessment activitiesInteractions of reading and assessment activities
Interactions of reading and assessment activities
 
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...
Parallel Construction: A Parallel Corpus Approach for Automatic Question Gene...
 
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for Education
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for EducationYAI4Edu: an Explanatory AI to Generate Interactive e-Books for Education
YAI4Edu: an Explanatory AI to Generate Interactive e-Books for Education
 
Automatic Question Generation for Evidence-based Online Courseware Engineering
Automatic Question Generation for Evidence-based Online Courseware EngineeringAutomatic Question Generation for Evidence-based Online Courseware Engineering
Automatic Question Generation for Evidence-based Online Courseware Engineering
 
Reading Comprehension Quiz Generation using Generative Pre-trained Transformers
Reading Comprehension Quiz Generation using Generative Pre-trained TransformersReading Comprehension Quiz Generation using Generative Pre-trained Transformers
Reading Comprehension Quiz Generation using Generative Pre-trained Transformers
 
Mathematical Language Processing via Tree Embeddings
Mathematical Language Processing via Tree EmbeddingsMathematical Language Processing via Tree Embeddings
Mathematical Language Processing via Tree Embeddings
 
Contextual Definition Generation
Contextual Definition GenerationContextual Definition Generation
Contextual Definition Generation
 
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...
Transforming Textbooks into Learning by Doing Environments: An Evaluation of ...
 
Generation of Assessment Questions from Textbooks Enriched with Knowledge Models
Generation of Assessment Questions from Textbooks Enriched with Knowledge ModelsGeneration of Assessment Questions from Textbooks Enriched with Knowledge Models
Generation of Assessment Questions from Textbooks Enriched with Knowledge Models
 
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...Using Semantics of Textbook Highlights to Predict Student Comprehension and K...
Using Semantics of Textbook Highlights to Predict Student Comprehension and K...
 
Dental TutorBot: Exploitation of Dental Textbooks for Automated Learning
Dental TutorBot: Exploitation of Dental Textbooks for Automated LearningDental TutorBot: Exploitation of Dental Textbooks for Automated Learning
Dental TutorBot: Exploitation of Dental Textbooks for Automated Learning
 
What's in a textbook
What's in a textbookWhat's in a textbook
What's in a textbook
 
Using Programmed Instruction to Help Students Engage with eTextbook Content
Using Programmed Instruction to Help Students Engage with eTextbook Content Using Programmed Instruction to Help Students Engage with eTextbook Content
Using Programmed Instruction to Help Students Engage with eTextbook Content
 
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...
Adding Intelligence to a Textbook for Human Anatomy with a Causal Concept Map...
 

Recently uploaded

Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024AyushiRastogi48
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett SquareIsiahStephanRadaza
 
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
TOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsTOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsssuserddc89b
 
Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2John Carlo Rollon
 
Transposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptTransposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptArshadWarsi13
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxdharshini369nike
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxSwapnil Therkar
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxEran Akiva Sinbar
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxNandakishor Bhaurao Deshmukh
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...lizamodels9
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxVarshiniMK
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Speech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxSpeech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxpriyankatabhane
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxpriyankatabhane
 
insect anatomy and insect body wall and their physiology
insect anatomy and insect body wall and their  physiologyinsect anatomy and insect body wall and their  physiology
insect anatomy and insect body wall and their physiologyDrAnita Sharma
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Masticationvidulajaib
 

Recently uploaded (20)

Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett Square
 
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
TOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsTOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physics
 
Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2
 
Transposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptTransposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.ppt
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptx
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptx
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Speech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxSpeech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptx
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
 
insect anatomy and insect body wall and their physiology
insect anatomy and insect body wall and their  physiologyinsect anatomy and insect body wall and their  physiology
insect anatomy and insect body wall and their physiology
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Mastication
 

Toward Eliminating Hallucinations: GPT-based Explanatory AI for Intelligent Textbooks and Documentation

  • 1. Toward Eliminating Hallucinations F. Sovrano, K. Ashley, A. Bacchelli GPT-based Explanatory AI for Intelligent Textbooks and Documentation
  • 2. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 2
  • 3. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 3
  • 4. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 4
  • 5. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 5
  • 6. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 6
  • 7. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 7
  • 8. Outline The contents of this presentation will be organised as follows: • Introduction • Background • Proposed Approach • Experiment • Discussion • Conclusions 8
  • 9. Problem and Motivation • Problem: Too much static information. How to explain it? • Advancements in NLP, such as models like ChatGPT, can provide dynamic explanations. • However, these models introduce challenges like hallucinations. • Memory constraints are another challenge associated with using NLP models for dynamic explanations. 9
  • 10. Problem and Motivation • Problem: Too much static information. How to explain it? • Advancements in NLP, such as models like ChatGPT, can provide dynamic explanations. • However, these models introduce challenges like hallucinations. • Memory constraints are another challenge associated with using ChatGPT. 10
  • 11. Problem and Motivation • Problem: Too much static information. How to explain it? • Advancements in NLP, such as models like ChatGPT, can provide dynamic explanations. • However, these models introduce challenges like hallucinations. • Memory constraints are another challenge associated with using ChatGPT. 11
  • 12. Problem and Motivation • Problem: Too much static information. How to explain it? • Advancements in NLP, such as models like ChatGPT, can provide dynamic explanations. • However, these models introduce challenges like hallucinations. • Memory constraints are another challenge associated with using ChatGPT. 12
  • 13. Proposal: ExplanatoryGPT • ExplanatoryGPT is a combination of ChatGPT with answer retrieval algorithms. • It’s designed to address memory constraints and hallucinations • ExplanatoryGPT integrates question generation and answer retrieval algorithms. It’s based on Achinstein's theory of explanations to address the abovementioned issues. • Hallucination: the generation of content that does not maintain fidelity to a given context or source. 13
  • 14. Proposal: ExplanatoryGPT • ExplanatoryGPT is a combination of ChatGPT with answer retrieval algorithms. • It’s designed to address memory constraints and hallucinations • ExplanatoryGPT integrates question generation and answer retrieval algorithms. It’s based on Achinstein's theory of explanations to address the abovementioned issues. • Hallucination: the generation of content that does not maintain fidelity to a given context or source. 14
  • 15. Proposal: ExplanatoryGPT • ExplanatoryGPT is a combination of ChatGPT with answer retrieval algorithms. • It’s designed to address memory constraints and hallucinations • ExplanatoryGPT integrates question generation and answer retrieval algorithms. It’s based on Achinstein's theory of explanations to address the abovementioned issues. • Hallucination: the generation of content that does not maintain fidelity to a given context or source. 15
  • 16. Proposal: ExplanatoryGPT • ExplanatoryGPT is a combination of ChatGPT with answer retrieval algorithms. • It’s designed to address memory constraints and hallucinations • ExplanatoryGPT integrates question generation and answer retrieval algorithms. It’s based on Achinstein's theory of explanations to address the abovementioned issues. • Hallucination: the generation of content that does not maintain fidelity to a given context or source. 16
  • 17. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): – Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. – It’s the difference between answering questions and explaining. • Example: “How are you?” – “Alright”: not an explanation. – “I’m good, because I just successfully defended my PhD, etc.” 17
  • 18. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): • Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. • It’s the difference between answering questions and explaining. • Example: “How are you?” • “Alright”: not an explanation. • “I’m good, because I just successfully defended my PhD, etc.” 18
  • 19. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): • Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. • It’s the difference between answering questions and explaining. • Example: “How are you?” – “Alright”: not an explanation. – “I’m good, because I just successfully defended my PhD, etc.” 19
  • 20. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): • Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. • It’s the difference between answering questions and explaining. • Example: “How are you?” • “Alright”: not an explanation. • “I’m good, because I just successfully defended my PhD, etc.” 20
  • 21. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): • Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. • It’s the difference between answering questions and explaining. • Example: “How are you?” • “Alright”: not an explanation. • “I’m good, because I just successfully defended my PhD, etc.” 21
  • 22. Background • Achinstein: Explaining is an illocutionary act with the intention to provide new understandings to the explainee by answering questions. • Illocution (in explanations): • Equivalent to pertinently anticipating implicit (archetypal) questions, e.g., Why? What for? How? When? etc. • It’s the difference between answering questions and explaining. • Example: “How are you?” • “Alright”: not an explanation. • “I’m good, because I just successfully defended my PhD, etc.” 22
  • 23. Why Achinstein’s Theory? • This definition of illocution is computer-friendly. We can use linguistic theories to define and generate implicit archetypal questions and AI can help us estimate how pertinently they are answered. • Our tech: textbook or documentation information is extracted and organised by question-answering algorithms. • ChatGPT is used to refine the retrieved information, improving readability, coherence, and cohesion. 23
  • 24. Why Achinstein’s Theory? • This definition of illocution is computer-friendly. We can use linguistic theories to define and generate implicit archetypal questions and AI can help us estimate how pertinently they are answered. • Our tech: answer retrieval algorithms which can extract information out of textbooks or documentation. • ChatGPT is used to refine the retrieved information, improving readability, coherence, and cohesion. 24
  • 25. Why Achinstein’s Theory? • This definition of illocution is computer-friendly. We can use linguistic theories to define and generate implicit archetypal questions and AI can help us estimate how pertinently they are answered. • Our tech: answer retrieval algorithms which can extract information out of textbooks or documentation. • We use ChatGPT to refine the retrieved information, improving readability, coherence, and cohesion. 25
  • 26. Example: Q&A for Explaining 26
  • 27. The Technology in a Nutshell 27
  • 29. Applications We applied ExplanatoryGPT to • a law textbook, • Software documentation of: • a credit approval system, • a heart disease predictor. 29
  • 30. Applications We applied ExplanatoryGPT to • a law textbook, • software documentation of • a credit approval system, • a heart disease predictor. 30
  • 31. Applications We applied ExplanatoryGPT to • a law textbook, • software documentation of ‣ a credit approval system, • a heart disease predictor. 31
  • 32. Applications We applied ExplanatoryGPT to • a law textbook, • software documentation of ‣ a credit approval system, ‣ a heart disease predictor. 32
  • 34. Proof of Concept 34 An AI decides to deny a loan
  • 35. Proof of Concept 35 An XAI explains why
  • 36. Proof of Concept 36 John can access external documentation/explanations
  • 37. Proof of Concept 37 An overview is opened
  • 38. 38 Connected to other overviews Proof of Concept
  • 39. 39 Intelligent annotation: not all words are underlined Proof of Concept
  • 40. 40 Illocution is used to anchor pertinent contents Credit Approval System
  • 41. 41 ChatGPT re-writes and amalgamates the retrieved answers Proof of Concept
  • 42. 42 There is also room for user-defined questions Proof of Concept
  • 43. Small Experiment • We compared ChatGPT with ExplanatoryGPT on the law textbook. 43
  • 44. Small Experiment • We compared ChatGPT with ExplanatoryGPT on the law textbook. 44 ChatGPT’s prompt
  • 45. Small Experiment • We compared ChatGPT with ExplanatoryGPT on the law textbook. 45 ExplanatoryGPT’s prompt
  • 49. Discussion • ChatGPT could be fed with the whole explanation context necessary for generating appropriate responses. • But without a filtering mechanism we would hit ChatGPT's memory constraints. • ChatGPT cannot process more than a few pages. • Our YAI doesn’t have this problem. We use answer retrieval to generate accurate and context-specific outputs. 49
  • 50. Discussion • ChatGPT could be fed with the whole explanation context necessary for generating appropriate responses. • But without a filtering mechanism we would hit ChatGPT's memory constraints. • ChatGPT cannot process more than a few pages. • Our YAI doesn’t have this problem. We use answer retrieval to generate accurate and context-specific outputs. 50
  • 51. Discussion • ChatGPT could be fed with the whole explanation context necessary for generating appropriate responses. • But without a filtering mechanism we would hit ChatGPT's memory constraints. • ChatGPT cannot process more than a few pages. • Our YAI doesn’t have this problem. We use answer retrieval to generate accurate and context-specific outputs. 51
  • 52. Discussion • ChatGPT could be fed with the whole explanation context necessary for generating appropriate responses. • But without a filtering mechanism we would hit ChatGPT's memory constraints. • ChatGPT cannot process more than a few pages. • Our YAI doesn’t have this problem. We use answer retrieval to generate accurate and context-specific outputs. 52
  • 53. More Discussion • The answer retrieval mechanism is used for macro-planning: the selection of information. • ChatGPT is then used for surface realisation. • Thus, ExplanatoryGPT can provide specific and context-aware explanations, avoiding broad or incorrect responses. 53
  • 54. More Discussion • The answer retrieval mechanism is used for macro-planning: the selection of information. • ChatGPT is then used for surface realisation. • Thus, ExplanatoryGPT can provide specific and context-aware explanations, avoiding broad or incorrect responses. 54
  • 55. More Discussion • The answer retrieval mechanism is used for macro-planning: the selection of information. • ChatGPT is then used for surface realisation. • Thus, ExplanatoryGPT can provide specific and context-aware explanations, avoiding broad or incorrect responses. 55
  • 56. Conclusions • Answer retrieval and ChatGPT complement each other. • This methodology has potential for improving explanations in intelligent textbooks and documentation. • Future research: – experiments to verify whether ExplanatoryGPT helps enhancing educational materials and software documentation; – experiments to verify whether ExplanatoryGPT is better than ChatGPT. 56
  • 57. Conclusions • Answer retrieval and ChatGPT complement each other. • This methodology has potential for improving explanations in intelligent textbooks and documentation. • Future research: – experiments to verify whether ExplanatoryGPT helps enhancing educational materials and software documentation; – experiments to verify whether ExplanatoryGPT is better than ChatGPT. 57
  • 58. Conclusions • Answer retrieval and ChatGPT complement each other. • This methodology has potential for improving explanations in intelligent textbooks and documentation. • Future research: • experiments to verify whether ExplanatoryGPT helps enhancing educational materials and software documentation; • experiments to verify whether ExplanatoryGPT is better than ChatGPT. 58
  • 59. Conclusions • Answer retrieval and ChatGPT complement each other. • This methodology has potential for improving explanations in intelligent textbooks and documentation. • Future research: • experiments to verify whether ExplanatoryGPT helps enhancing educational materials and software documentation; • experiments to verify whether ExplanatoryGPT is better than ChatGPT. 59
  • 61. 61
  • 62. Speaker: Francesco Sovrano Email: francesco.sovrano@uzh.ch