activity
20222025
most citedCUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning

7 citations · 9 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL20252 cited

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Bang An, Shiyue Zhang, Mark Dredze

Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…

cs.LG2025

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

Juntao Dai, Taiye Chen, Yaodong Yang +2

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an o…

cs.LG2025

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

Jiaming Ji, Xinyu Chen, Rui Pan +13

Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of…

cs.CL2025

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.LG2024

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation

Juntao Dai, Yaodong Yang, Qian Zheng +1

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy…

cs.CL2024

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback

Jiayi Zhou, Jiaming Ji, Juntao Dai +2

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs b…