activity
20242026
most citedRethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective

2 citations · 4 across the 11 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses

Jimin Mun, Chani Jung, Xuhui Zhou +2

While LLMs hold significant potential to transform scientific research, we advocate for their use to augment and empower researchers rather than to automate research without human…

cs.AI2025

Social World Models

Xuhui Zhou, Jiarui Liu, Akhila Yerukola +2

Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems str…

cs.AI2025

1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning

Wenkai Li, Liwen Sun, Zhenxiang Guan +2

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing m…

cs.AI2024

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

Xuhui Zhou, Hyunwoo Kim, Faeze Brahman +9

AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examini…

cs.AI2024

AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents

Zhe Su, Xuhui Zhou, Sanketh Rangreji +4

Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conf…

cs.AI2024

On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

Jen-tse Huang, Jiaxu Zhou, Tailin Jin +6

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. Howeve…