9 papers
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
Lance Ying, Jinzhou Wu, Yingshan Susan Wang +53
Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in what ways…
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3
Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict.…
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Baicheng Chen, Zheyuan Liu, Jingyu Zhang +4
Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alo…
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…
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…
The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
Yunze Xiao, Vivienne J. Zhang, Chenghao Yang +3
Large language models (LLMs) have powered multi-agent simulations such as survey respondents or application users. However, LLMs lack the population-level diversity required by the…
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…
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…
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…