8 papers
Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
Yuxuan Li, Aoi Naito, Hirokazu Shirado
Multi-agent systems built on large language models (LLMs) are expected to enhance decision-making by pooling distributed information, yet systematically evaluating this capability…
WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning
Yuxuan Li, Kyzyl Monteiro, Hirokazu Shirado +1
Policymakers in domains such as emergency management, public health, and urban planning must make decisions under deep uncertainty, where outcomes depend on how large populations i…
How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
Yuxuan Li, Leyang Li, Hao-Ping Lee +1
A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form attitudes toward and behave in response to security and privacy (…
What Makes LLM Agent Simulations Useful for Policy Practice? An Iterative Design Study in Emergency Preparedness
Yuxuan Li, Sauvik Das, Hirokazu Shirado
Policymakers must often act under conditions of deep uncertainty, such as emergency response, where predicting the specific impacts of a policy apriori is implausible. Large Langua…
Spontaneous Giving and Calculated Greed in Language Models
Yuxuan Li, Hirokazu Shirado
Large language models demonstrate strong problem-solving abilities through reasoning techniques such as chain-of-thought prompting and reflection. However, it remains unclear wheth…
Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models
Yuxuan Li, Hirokazu Shirado, Sauvik Das
While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may…