OMVV：成本约束下语言模型响应的在线多验证器校验

View PDF HTML (experimental)

Abstract:As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintaining reliability at scale. Verifying the correctness of large language model outputs is often done by querying a costly ground-truth oracle, which is impractical to invoke at every step in an online setting. Prior work addresses this by querying a single weak verifier on every step, and using its score to decide whether the costly strong verifier needs to be queried as well, reserving strong verification for only a small fraction of the steps. However, a single fixed weak verifier may not perform consistently well as the subject matter or difficulty of incoming queries changes over time, and committing to one in advance risks either overly costly or inaccurate verification. We introduce OMVV (Online Multi-Verifier Verification), an algorithm that maintains a pool of $K$ candidate weak verifiers with differing cost and verification performance, and adaptively routes each round's decision to a verifier selected via an online score combiner and an exponential-weights routing policy. OMVV provides a distribution-free, finite-time guarantee on false-accept and false-reject rates across the full pool of verifiers, and further achieves sublinear regret against the best fixed verifier in hindsight under a combined cost and consistency objective. Experiments on reasoning dataset benchmarks show that OMVV achieves higher accuracy at lower verification cost than any single fixed verifier, across a range of operating budgets.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.02632 [cs.LG]
	(or arXiv:2610.02632v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.02632 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Erfan Hajihashemi [view email]
[v1] Fri, 2 Oct 2026 00:45:36 UTC (103 KB)