works on

From the 1 of 37 linked papers with an AI index.

most citedReimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration

2 citations · 2 across the 18 of their papers we have counts for

collaborators
Showing cs.CLShow all

12 papers · 1 filter

cs.CL2026

ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance

Haoran Li, Yulin Chen, Huihao Jing +6

Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context…

cs.CL2026

Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors

Pengcheng Wen, Yanxu Zhu, Jiapeng Sun +5

Chain-of-Thought (CoT) is often viewed as a window into LLM decision-making, yet recent work suggests it may function merely as post-hoc rationalization. This raises a critical ali…

cs.CL2026

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs

Pengcheng Wen, Jiaming Ji, Chi-Min Chan +5

Large language models (LLMs) have demonstrated enhanced performance through the \textit{Thinking then Responding} paradigm, where models generate internal thoughts before final res…

cs.CL2026

AMSafety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs

Han Zhu, Jiale Chen, Chengkun Cai +8

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal s…

cs.CL2025

SafeMT: Multi-turn Safety for Multimodal Language Models

Han Zhu, Juntao Dai, Jiaming Ji +8

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interacti…

cs.CL2025

Semantic-guided Diverse Decoding for Large Language Model

Weijie Shi, Yue Cui, Yaguang Wu +7

Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than…