5 papers
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
Wentao Zhang, Haoyu Zhang, Xinke Jiang +7
Large Language Models (LLMs) excel at multi-step reasoning, yet current parallel reasoning approaches often fail to distinguish the contributions of individual reasoning paths. Man…
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
Yuyou Zhang, Miao Li, William Han +3
Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or represen…
CrashAgent: Crash Scenario Generation via Multi-modal Reasoning
Miao Li, Wenhao Ding, Haohong Lin +4
Training and evaluating autonomous driving algorithms requires a diverse range of scenarios. However, most available datasets predominantly consist of normal driving behaviors demo…
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training
Yihang Yao, Zhepeng Cen, Miao Li +6
Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlyi…
Privacy Risks in Reinforcement Learning for Household Robots
Miao Li, Wenhao Ding, Ding Zhao
The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, o…