Model-Based Trust Analysis of LLM Conversations
Pages 602 - 610
Abstract
LLM-based chatbots are routinely advertised as supporting the collaboration of humans and AI. We study LLM conversations from a knowledge elicitation perspective with the objective of being able to understand and assess the human's trust in knowledge elicited from the LLM and complementary sources. Our approach is supported by the DSML KEML, the Knowledge Elicitation Modeling Language, subject to abstract and visual syntax as well as a model transformation-based model semantics for trust analysis. Conversations are modeled by a combination of sequence diagrams and enhanced argumentation graphs --- the latter for the purpose of relating information pieces (facts and instructions) that are extracted from messages. The analysis of the corresponding models entails trust scores for gathered information (i.e., elicited knowledge).
References
[1]
Leila Amgoud, Jonathan Ben-Naim, Dragan Doder, and Srdjan Vesic. 2017. Acceptability Semantics for Weighted Argumentation Frameworks. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19--25, 2017, Carles Sierra (Ed.). ijcai.org, 56--62.
[2]
Leila Amgoud and Claudette Cayrol. 1998. On the Acceptability of Arguments in Preference-based Argumentation. In UAI '98: Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, Gregory F. Cooper and Serafín Moral (Eds.). Morgan Kaufmann, 1--7. https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=226&proceeding_id=14
[3]
Shouvik Ahmed Antu, Haiyan Chen, and Cindy K. Richards. 2023. Using LLM (Large Language Model) to Improve Efficiency in Literature Review for Undergraduate Research (CEUR Workshop Proceedings, Vol. 3487), Steven Moore, John C. Stamper, Richard Tong, Chen Cao, Zitao Liu, Xiangen Hu, Yu Lu, Joleen Liang, Hassan Khosravi, Paul Denny, Anjali Singh, and Chris Brooks (Eds.). CEUR-WS.org, 8--16. https://ceur-ws.org/Vol-3487/short2.pdf
[4]
Pietro Baroni, Marco Romano, Francesca Toni, Marco Aurisicchio, and Giorgio Bertanza. 2015. Automatic evaluation of design alternatives with quantitative argumentation. Argument Comput. 6, 1 (2015), 24--49.
[5]
Pietro Baroni, Francesca Toni, and Bart Verheij. 2020. On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games: 25 years later. Argument Comput. 11, 1--2 (2020), 1--14.
[6]
Trevor Bench-Capon. 2002. Value-based argumentation frameworks. NMR, 443--454.
[7]
Philippe Besnard and Anthony Hunter. 2001. A logic-based theory of deductive arguments. Artif. Intell. 128, 1--2 (2001), 203--235.
[8]
Dominik Bork, Philip Langer, and Tobias Ortmayr. 2023. A Vision for Flexible GLSP-Based Web Modeling Tools. In The Practice of Enterprise Modeling - 16th IFIP Working Conference, PoEM 2023, Vienna, Austria, November 28 - December 1, 2023, Proceedings (Lecture Notes in Business Information Processing, Vol. 497), João Paulo A. Almeida, Monika Kaczmarek-Heß, Agnes Koschmider, and Henderik A. Proper (Eds.). Springer, 109--124.
[9]
Markus Brenneis, Maike Behrendt, and Stefan Harmeling. 2021. How Will I Argue? A Dataset for Evaluating Recommender Systems for Argumentations. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Singapore and Online, 360--367. https://aclanthology.org/2021.sigdial-1.38
[10]
Claudette Cayrol and Marie-Christine Lagasquie-Schiex. 2005. On the Acceptability of Arguments in Bipolar Argumentation Frameworks. 378--389.
[11]
Newton C. A. Da Costa and Steven French. 1989. On the Logic of Belief. Philosophy and Phenomenological Research 49, 3 (1989), 431--446. http://www.jstor.org/stable/2107797
[12]
Louise Dupuis de Tarlé, Elise Bonzon, and Nicolas Maudet. 2022. Multiagent Dynamics of Gradual Argumentation Semantics. In 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 363--371.
[13]
Phan Minh Dung. 1995. On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artificial Intelligence 77, 2 (1995), 321--357.
[14]
Matthew Gentzkow, Michael B. T. Wong, and Allen Zhang. 2018. Ideological Bias and Trust in Information Sources. Working paper https://www.hbs.edu/faculty/Pages/item.aspx?num=54349.
[15]
Fabrizio Gilardi, Meysam Alizadeh, and Maël Kubli. 2023. ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks. arXiv:2303.15056 [cs.CL]
[16]
Aumyo Hassan and Sarah Barber. 2021. The effects of repetition frequency on the illusory truth effect. Cognitive Research: Principles and Implications 6 (12 2021).
[17]
Antonis C. Kakas, Pavlos Moraitis, and Nikolaos I. Spanoudakis. 2019. GORGIAS: Applying argumentation. Argument Comput. 10, 1 (2019), 55--81.
[18]
John Kingston. 2004. Conducting feasibility studies for knowledge based systems. Knowl. Based Syst. 17, 2--4 (2004), 157--164.
[19]
John Kingston and Ann Macintosh. 2000. Knowledge management through multi-perspective modelling: Representing and distributing organizational memory. Knowledge-Based Systems 13 (04 2000), 121--131.
[20]
Himabindu Lakkaraju, Dylan Slack, Yuxin Chen, Chenhao Tan, and Sameer Singh. [n. d.]. Rethinking Explainability as a Dialogue: A Practitioner's Perspective. NeurIPS Workshop on Human Centered AI ([n. d.]). https://par.nsf.gov/biblio/10462932
[21]
Scott Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. 4765--4774.
[22]
Luis Palacios Medinacelli, Florian Noyrit, and Chokri Mraidha. 2022. Augmenting model-based systems engineering with knowledge. In Proceedings of the 25th International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings, MODELS 2022. ACM, 351--358.
[23]
Microsoft. 2018. Language Server Protocol. https://microsoft.github.io/language-server-protocol/
[24]
J. D. Novak and A. J. Cañas. 2008. The Theory Underlying Concept Maps and How to Construct and Use Them. Technical Report. Technical Report IHMC Cmap-Tools 2006-01 Rev 01-2008, Florida Institute for Human and Machine Cognition. Available at http://cmap.ihmc.us/docs/pdf/TheoryUnderlyingConceptMaps.pdf.
[25]
NVD. 2023. CVE entry 2021-44228. https://nvd.nist.gov/vuln/detail/CVE-2021-44228. Last Accessed: 21.11.2023.
[26]
Charnon Pattiyanon, Toshiaki Aoki, and Daisuke Ishii. 2022. A Method for Detecting Common Weaknesses in Self-Sovereign Identity Systems Using Domain-Specific Models and Knowledge Graph. In Proceedings of the 10th International Conference on Model-Driven Engineering and Software Development, MODEL-SWARD 2022. SCITEPRESS, 219--226.
[27]
Hammond Pearce, Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, and Ramesh Karri. 2022. Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions. In 43rd IEEE Symposium on Security and Privacy, SP 2022. IEEE, 754--768.
[28]
Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick S. H. Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander H. Miller. 2019. Language Models as Knowledge Bases?. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019. Association for Computational Linguistics, 2463--2473.
[29]
Antonio Rago, Oana Cocarascu, and Francesca Toni. 2018. Argumentation-Based Recommendations: Fantastic Explanations and How to Find Them. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18. International Joint Conferences on Artificial Intelligence Organization, 1949--1955.
[30]
Antonio Rago, Hengzhi Li, and Francesca Toni. 2023. Interactive Explanations by Conflict Resolution via Argumentative Exchanges. In Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning, KR 2023. 582--592.
[31]
Francisco Ribeiro, José Nuno Castro de Macedo, Kanae Tsushima, Rui Abreu, and João Saraiva. 2023. GPT-3-Powered Type Error Debugging: Investigating the Use of Large Language Models for Code Repair. In Proceedings of the 16th ACM SIGPLAN International Conference on Software Language Engineering, SLE 2023. ACM, 111--124.
[32]
Nigel R. Shadbolt and Paul R. Smart. 2015. Knowledge elicitation. In Evaluation of human work, 4th Edition, R. Wilson and Sarah Sharples (Eds.). CRC press Boca Raton, 163--200.
[33]
Henrik Smedberg and Sunith Bandaru. 2023. Interactive knowledge discovery and knowledge visualization for decision support in multi-objective optimization. European Journal of Operational Research 306, 3 (2023), 1311--1329.
[34]
Caleb Ziems, William Held, Omar Shaikh, Jiaao Chen, Zhehao Zhang, and Diyi Yang. 2023. Can Large Language Models Transform Computational Social Science? https://arxiv.org/abs/2305.03514.
Index Terms
- Model-Based Trust Analysis of LLM Conversations
Recommendations
Combining fUML and profiles for non-functional analysis based on model execution traces
QoSA '13: Proceedings of the 9th international ACM Sigsoft conference on Quality of software architecturesFor developing software systems it is crucial to consider non-functional properties already in an early development stage to guarantee that the system will satisfy its non-functional requirements. Following the model-based engineering paradigm ...
Extending UML Sequence Diagrams to Model Trust-dependent Behavior With the Aim to Support Risk Analysis
UML sequence diagrams are intuitively simple and can be understood by most stakeholders, including end-users, decision makers, engineers and other parties involved in a risk analysis. Building on UML sequence diagrams and trying to maintain their ...
A General Trust Model Based on Trust Algebra
MINES '09: Proceedings of the 2009 International Conference on Multimedia Information Networking and Security - Volume 01The growing importance of Trust in the realm of open network environment introduces further research on it, due to the special significance of trust to whole system. We view trust as a relation among entities that participate in an action meeting the ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2024
1261 pages
ISBN:9798400706226
DOI:10.1145/3652620
- Chairs:
- Manuel Wimmer,
- Alexander Egyed,
- Program Chairs:
- Benoit Combemale,
- Marsha Chechik
Copyright © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
- SIGSOFT: ACM Special Interest Group on Software Engineering
- Johannes Kepler University Linz
- IEEE CS
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 31 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
Conference
MODELS Companion '24
Sponsor:
MODELS Companion '24: ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems
September 22 - 27, 2024
Linz, Austria
Acceptance Rates
Overall Acceptance Rate 144 of 506 submissions, 28%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 95Total Downloads
- Downloads (Last 12 months)95
- Downloads (Last 6 weeks)57
Reflects downloads up to 01 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in