← Search

Linchen Xiao

2 accepted papers

2025

Are Your LLMs Capable of Stable Reasoning?

ACL 2025finding

The rapid advancement of large language models (LLMs) has shown remarkable progress in complex reasoning tasks. However, a significant disparity exists between benchmark performances and real-world applications. We attribute this gap primarily to current evaluation protocols and metrics, which inade…

2025

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

EMNLP 2025

Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward model to guide LLM optimization. Most evaluation frameworks rely on regularized matching or employ general LLMs for answe