9 papers
Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment
Haokai Zhao, Yunze Xiao, Weihao Xuan +3
Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophancy, a well-documented by-pro…
ExpressionCueLens: A Cross-Cultural Analysis of Human-AI Companion Conversations on Social Media
Lynnette Hui Xian Ng, Yunze Xiao, Lionel Z. Wang +2
LLM-based AI companion agents are increasingly being perceived not only as tools but also as social companions. On social media, people recount conversations where these agents com…
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
Jiarui Liu, Lechen Zhang, Yongjin Yang +5
Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain perform…
Knowledge Index of Noah's Ark
Sheng Jin, Minghao Liu, Yunze Xiao +24
Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotation that permits lazy consen…
The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
Yunze Xiao, Vivienne J. Zhang, Chenghao Yang +3
Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{P…
Say Something Else: Rethinking Contextual Privacy as Information Sufficiency
Yunze Xiao, Wenkai Li, Xiaoyuan Wu +3
LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only…