3 papers
cs.LG2025
Soundness-Aware Level: A Microscopic Signature that Predicts LLM Reasoning Potential
Xuansheng Wu, Xiaoman Pan, Wenlin Yao +1
Reinforcement learning with verifiable rewards (RLVR) can elicit strong reasoning in large language models (LLMs), while their performance after RLVR varies dramatically across dif…
cs.CL2025
Thrust: Adaptively Propels Large Language Models with External Knowledge
Xinran Zhao, Hongming Zhang, Xiaoman Pan +3
Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, maki…
cs.LG2024
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Rui Yang, Xiaoman Pan, Feng Luo +4
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is g…