collaborators

6 papers

cs.HC2026

Exploring the Interaction of Explanation Styles, Context, and Trust of AI Privacy Redaction in AI-mediated Interactions

Roshni Kaushik, Maarten Sap, Koichi Onoue

AI-mediated communication is increasingly being utilized to help facilitate interactions; however, in privacy sensitive domains, an AI mediator has the additional challenge of cons…

cs.AI2026

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

Wenkai Li, Fan Yang, Ananya Hazarika +2

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchr…

cs.MA2026

SOTOPIA-TOM: Evaluating Information Management in Multi-Agent Interaction with Theory of Mind

Yashwanth YS, Ruichen Wang, Shihua Zeng +4

As LLM-based agents are increasingly interacting in multi-party settings, they need to properly handle information asymmetry, i.e., knowing when and to whom to disclose information…

cs.AI2026

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs

Wenkai Li, Fan Yang, Shaunak A. Mehta +1

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering e…

cs.HC2026

Examining the Effect of Explanations of AI Privacy Redaction in AI-mediated Interactions

Roshni Kaushik, Maarten Sap, Koichi Onoue

AI-mediated communication is increasingly being utilized to help facilitate interactions; however, in privacy sensitive domains, an AI mediator has the additional challenge of cons…

cs.CL2026

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Xiaoyuan Wu, Roshni Kaushik, Wenkai Li +2

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to sh…