4 papers
Off-Manifold Collapse in Guided Protein Language Models
Shuibai Zhang, Xinchi Liu, Fred Zhangzhi Peng +4
Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative to fine-tuning. Such guidan…
Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors
Yangfan Hu, Xuhan Tong, Haoyue Bai +5
Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or wh…
Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL
Xuhan Tong, Yuchen Zeng, Jiawei Zhang
In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Althoug…
Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
Xiyue Peng, Hengquan Guo, Jiawei Zhang +4
Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training s…