5 papers
The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
Xinyu Zhu, Mengzhou Xia, Zhepei Wei +3
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoT…
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
Hongjin Su, Howard Yen, Mengzhou Xia +12
Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually…
SimPO: Simple Preference Optimization with a Reference-Free Reward
Yu Meng, Mengzhou Xia, Danqi Chen
Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback…
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…
LitSearch: A Retrieval Benchmark for Scientific Literature Search
Anirudh Ajith, Mengzhou Xia, Alexis Chevalier +3
Literature search questions, such as "Where can I find research on the evaluation of consistency in generated summaries?" pose significant challenges for modern search engines and…