2 papers
cs.CL2025
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Ding Chen, Qingchen Yu, Pengyuan Wang +9
With the release of OpenAI's o1 model, reasoning models that adopt slow-thinking strategies have become increasingly common. Their outputs often contain complex reasoning, intermed…
cs.LG2025
Adversarial Preference Learning for Robust LLM Alignment
Yuanfu Wang, Pengyu Wang, Chenyang Xi +13
Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to th…