arXiv:2602. 23248v2 Announce Type: replace Abstract: As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems.
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 AI.
Discover how prover-verifier games improve the legibility of language model outputs, making AI solutions clearer, easier to verify, and more trustworthy for both humans and machines.
The paper identifies a new failure mode in neurosymbolic systems called Verdict‑Preserving‑Unfaithfulness (VPU), where incorrect formal encodings can still pass solver checks. It introduces Generative Verification (GenV), a method that uses a language model to produce a continuous reference‑equivalence score without relying on explicit localization. Experiments show GenV+HN achieves high AUROC, generalizes to unseen translators, and improves downstream agent performance by 11.3 points.
The paper introduces OMVV, an online multi-verifier algorithm that maintains a pool of weak verifiers with varying costs and performance. It adaptively selects a verifier each round using an online score combiner and exponential-weights routing, providing distribution-free guarantees on false-accept and false-reject rates. Experiments on reasoning benchmarks show OMVV achieves higher accuracy at lower verification cost than any single fixed verifier across different budgets.
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
arXiv:2608.28725v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final...
arXiv:2603. 03538v4 Announce Type: replace Abstract: Large Language Models (LLMs) using chain-of-thought reasoning have demonstrated great potential for solving complex reasoning and planning tasks.