collaborators

6 papers

cs.AI2026

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…

cs.CL2026

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma +3

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…

cs.CL2026

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…

cs.CR2026

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…

cs.CR2026

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

Anthony Hughes, Vasisht Duddu, N. Asokan +2

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms su…

cs.CL2025

How Private are Language Models in Abstractive Summarization?

Anthony Hughes, Ning Ma, Nikolaos Aletras

In sensitive domains such as medical and legal, protecting sensitive information is critical, with protective laws strictly prohibiting the disclosure of personal data. This poses…