arXiv:2606. 00437v1 Announce Type: new Abstract: Process reward models (PRMs) are widely used in language-model training with dense step-level supervision.
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 Machine Learning.
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.
The paper introduces LSR‑Ben, a benchmark designed to evaluate process reward models (PRMs) on scientific and logical reasoning tasks, addressing a gap left by existing math‑focused benchmarks. Experiments on 22 models reveal that PRMs and LLMs perform poorly in non‑mathematical domains, with LLMs tending to over‑identify errors while PRMs tend to overlook them. LSR‑Ben aims to spur research that broadens PRM applicability and improves LLM reasoning.
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.
arXiv:2608.22138v1 Announce Type: new Abstract: Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present...
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.