CompassVerifier-7B

Papers using or citing this model 2

• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward 50 citations · 2025 · Conference on Empirical Methods in Natural Language Processing · arXiv

  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...

• VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models 19 citations · 2025 · arXiv.org · arXiv

  Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorporation of reference-based reward systems within...