works on

From the 1 of 13 linked papers with an AI index.

collaborators

13 papers

cs.CL2026

The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues

Jocelyn Shen, Amina Luvsanchultem, Jessica Kim +6

The paper presents PUPPET, a taxonomy and dataset of over a thousand human‑LLM advice interactions, and studies how well language models can predict the amount of belief change the…

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.CY2026

CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries

Vasudha Varadarajan, Akhila Yerukola, Mona T. Diab +1

To interact with users fairly and without stereotyping, AI models must display cultural competency, i.e., the ability to infer and adapt to a user's implicitly signaled cultural va…

cs.CL2026

Lost in Delusion: Examining LLM Safety Under User Delusions and Distress

Andrew Aquilina, Chetna Nihalani, Vasudha Varadarajan +3

LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delusional beliefs. Prior work o…

cs.CY2026

When Should AI Read the Room? Public Perceptions of Social Intelligence in AI Agents

Leena Mathur, Jenny T. Liang, Vasudha Varadarajan +6

AI researchers have been advancing socially intelligent AI agents (Social-AI) across embodiments, from chatbots to physical robots. As Social-AI is increasingly deployed in everyda…

cs.HC2026

Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks

Alice Gao, Andrew N. Meltzoff, Maarten Sap +1

Despite a global user base adopting large language models (LLMs) for daily writing tasks, model suggestions tend to align with Western values. Research has shown users commonly acc…