8 papers
A Pilot Study on Detecting Software Design Patterns with Large Language Models: An Empirical Evaluation
Oishik Chowdhury, Bastin Tony Roy Savarimuthu, Sherlock A. Licorish
Design patterns provide reusable solutions to recurring software design problems. Automatically detecting these patterns in source code can help bootstrap new developers' understan…
Evaluating LLM Alignment With Human Trust Models
Anushka Debnath, Stephen Cranefield, Bastin Tony Roy Savarimuthu +1
Trust plays a pivotal role in enabling effective cooperation, reducing uncertainty, and guiding decision-making in both human interactions and multi-agent systems. Although it is s…
Why Do You Contribute to Stack Overflow? Understanding Cross-Cultural Motivations and Usage Patterns before the Age of LLMs
Sherlock A. Licorish, Elijah Zolduoarrati, Tony Savarimuthu +3
Understanding motivations of contributors for participating in community question and answer platforms is crucial for sustaining knowledge-sharing ecosystem, which is necessary to…
Social Norm Reasoning in Multimodal Language Models: An Evaluation
Oishik Chowdhury, Anushka Debnath, Bastin Tony Roy Savarimuthu
In Multi-Agent Systems (MAS), agents are designed with social capabilities, allowing them to understand and reason about social concepts such as norms when interacting with others…
Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies
Kavindu Warnakulasuriya, Prabhash Dissanayake, Navindu De Silva +4
The evolution of cooperation has been extensively studied using abstract mathematical models and simulations. Recent advances in Large Language Models (LLMs) and the rise of LLM ag…
Can LLMs Reason About Trust?: A Pilot Study
Anushka Debnath, Stephen Cranefield, Emiliano Lorini +1
In human society, trust is an essential component of social attitude that helps build and maintain long-term, healthy relationships which creates a strong foundation for cooperatio…