Header

UZH-Logo

Maintenance Infos

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


Sovrano, Francesco; Ashley, Kevin; Bacchelli, Alberto (2023). Toward Eliminating Hallucinations: GPT-based Explanatory AI for Intelligent Textbooks and Documentation. In: Tokyo’23: Fifth Workshop on Intelligent Textbooks (iTextbooks) at the 24th International Conference on Artificial Intelligence in Education (AIED’2023),, Tokyo, Japan, 3 July 2023 - 7 July 2023. CEUR-WS, 54-65.

Abstract

Traditional explanatory resources, such as user manuals and textbooks, often contain content that may not cater to the diverse backgrounds and information needs of users. Yet, developing intuitive, user-centered methods to effectively explain complex or large amounts of information is still an open research challenge. In this paper we present ExplanatoryGPT, an approach we devised and implemented to transform textual documents into interactive, intelligent resources, capable of offering dynamic, personalized explanations. Our approach uses state-of-the-art question-answering technology to generate on-demand, expandable explanations, with the aim of allowing readers to efficiently navigate and comprehend static materials. ExplanatoryGPT integrates ChatGPT, a state-of-the-art language model, with Achinstein’s philosophical theory of explanations. By combining question generation and answer retrieval algorithms with ChatGPT, our method generates interactive, user-centered explanations, while mitigating common issues associated with ChatGPT, such as hallucinations and memory shortcomings. To showcase the effectiveness of our Explanatory AI, we conducted tests using a variety of sources, including a legal textbook and documentation of some health and financial software. Specifically, we provide several examples that illustrate how ExplanatoryGPT excels over ChatGPT in generating more precise explanations, accomplished through thoughtful macro-planning of explanation content. Notably, our approach also avoids the need to provide the entire context of the explanation as a prompt to ChatGPT, a process that is often not feasible due to common memory constraints.

Abstract

Traditional explanatory resources, such as user manuals and textbooks, often contain content that may not cater to the diverse backgrounds and information needs of users. Yet, developing intuitive, user-centered methods to effectively explain complex or large amounts of information is still an open research challenge. In this paper we present ExplanatoryGPT, an approach we devised and implemented to transform textual documents into interactive, intelligent resources, capable of offering dynamic, personalized explanations. Our approach uses state-of-the-art question-answering technology to generate on-demand, expandable explanations, with the aim of allowing readers to efficiently navigate and comprehend static materials. ExplanatoryGPT integrates ChatGPT, a state-of-the-art language model, with Achinstein’s philosophical theory of explanations. By combining question generation and answer retrieval algorithms with ChatGPT, our method generates interactive, user-centered explanations, while mitigating common issues associated with ChatGPT, such as hallucinations and memory shortcomings. To showcase the effectiveness of our Explanatory AI, we conducted tests using a variety of sources, including a legal textbook and documentation of some health and financial software. Specifically, we provide several examples that illustrate how ExplanatoryGPT excels over ChatGPT in generating more precise explanations, accomplished through thoughtful macro-planning of explanation content. Notably, our approach also avoids the need to provide the entire context of the explanation as a prompt to ChatGPT, a process that is often not feasible due to common memory constraints.

Statistics

Downloads

310 downloads since deposited on 19 Feb 2024
310 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > General Computer Science
Scope:Discipline-based scholarship (basic research)
Language:English
Event End Date:7 July 2023
Deposited On:19 Feb 2024 13:50
Last Modified:06 Mar 2024 15:15
Publisher:CEUR-WS
Series Name:CEUR Workshop Proceedings
Number:3444
ISSN:1613-0073
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:https://ceur-ws.org/Vol-3444/itb23_s3p2.pdf
Project Information:
  • : FunderSNSF
  • : Grant ID00021_197227
  • : Project TitleEnhanced Code Review: Using Context and Learning from Review Experience
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)