arXiv Computation and Language By Zebei Zhao, Zhihao Shi, Minqi Shi

AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification

Read the original on arXiv Computation and Language →

AutoVerifier is a residual‑guided, non‑parametric optimization framework designed to improve reference‑based answer verification. It learns verifier inductive biases from recurring errors, records them as rule cards, and promotes them to code modules or prompt guidance only after replay validation ensures no regressions. Experiments on four verifier benchmarks show that AutoVerifier surpasses state‑of‑the‑art verifiers by a large margin.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Aug 28

From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning

The paper investigates the reliability of rule- and model-based verifiers used in reinforcement learning with verifiable reward (RLVR) for mathematical reasoning. It finds that rule-based verifiers often miss equivalent answers in different formats, causing false negatives that degrade RL performance as models improve. Model-based verifiers achieve higher static accuracy but become vulnerable to reward hacking during RL, misclassifying certain response patterns as correct after fine-tuning.

By Yuzhen Huang, Weihao Zeng, Xingshan Zeng, Qi Zhu, Junxian He
arXiv Machine Learning
Jul 28

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

arXiv:2602. 01348v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit.

By Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma