<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2025-prmbench">
    <titleInfo>
        <title>PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mingyang</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhaochen</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoye</namePart>
        <namePart type="family">Qu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiawei</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during the reasoning process, PRMs are required to possess nuanced capabilities for detecting various implicit error types in real-world scenarios. However, current benchmarks primarily focus on step correctness, failing to evaluate PRMs’ performance systematically. To address this gap, we introduce PRMBench, a process-level benchmark specifically designed to assess the fine-grained error detection capabilities of PRMs. PRMBench comprises 6,216 carefully designed problems and 83,456 step-level labels, evaluating models across multiple dimensions, including simplicity, soundness, and sensitivity. In our experiments on 25 models, spanning both open-source PRMs and closed-source large language models prompted as critic models, we uncover significant weaknesses in current PRMs. These findings underscore the challenges inherent in process-level evaluation and highlight key directions for future research, establishing PRMBench as a robust testbed for advancing research on PRM evaluation and development.</abstract>
    <identifier type="citekey">song-etal-2025-prmbench</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.1230</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.1230/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>25299</start>
            <end>25346</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
%A Song, Mingyang
%A Su, Zhaochen
%A Qu, Xiaoye
%A Zhou, Jiawei
%A Cheng, Yu
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F song-etal-2025-prmbench
%X Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during the reasoning process, PRMs are required to possess nuanced capabilities for detecting various implicit error types in real-world scenarios. However, current benchmarks primarily focus on step correctness, failing to evaluate PRMs’ performance systematically. To address this gap, we introduce PRMBench, a process-level benchmark specifically designed to assess the fine-grained error detection capabilities of PRMs. PRMBench comprises 6,216 carefully designed problems and 83,456 step-level labels, evaluating models across multiple dimensions, including simplicity, soundness, and sensitivity. In our experiments on 25 models, spanning both open-source PRMs and closed-source large language models prompted as critic models, we uncover significant weaknesses in current PRMs. These findings underscore the challenges inherent in process-level evaluation and highlight key directions for future research, establishing PRMBench as a robust testbed for advancing research on PRM evaluation and development.
%R 10.18653/v1/2025.acl-long.1230
%U https://aclanthology.org/2025.acl-long.1230/
%U https://doi.org/10.18653/v1/2025.acl-long.1230
%P 25299-25346

Markdown (Informal)

[PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models](https://aclanthology.org/2025.acl-long.1230/) (Song et al., ACL 2025)

• PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models (Song et al., ACL 2025)

ACL

• Mingyang Song, Zhaochen Su, Xiaoye Qu, Jiawei Zhou, and Yu Cheng. 2025. PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25299–25346, Vienna, Austria. Association for Computational Linguistics.