collaborators

7 papers

cs.AI2026

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control

Rui Ha, Rui Pu, Chaozhuo Li +2

Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. As a result, LRM…

cs.LG2026

Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches

Shaoke Fang, Ziang Li, Wenfei Wu +3

Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt prefixes to reduce expensive…

cs.CR2026

How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference

Songyang Liu, Chaozhuo Li, Rui Pu +5

Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications tha…

cs.CL2026

LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs

Chenxu Wang, Chaozhuo Li, Pengbo Wang +7

Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to…

cs.AI2025

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning

Rui Pu, Chaozhuo Li, Rui Ha +3

Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, whic…

cs.CR2025

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs

Rui Pu, Chaozhuo Li, Rui Ha +5

Jailbreak attack can be used to access the vulnerabilities of Large Language Models (LLMs) by inducing LLMs to generate the harmful content. And the most common method of the attac…