@inproceedings{zhang-etal-2025-reasonerrank,
title = "{R}easoner{R}ank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks",
author = "Zhang, Jiamu and
Yuan, Jiayi and
Wen, Andrew and
Le, Hoang Anh Duy and
Chuang, Yu-Neng and
Choi, Soo-Hyun and
Chen, Rui and
Hu, Xia",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.700/",
doi = "10.18653/v1/2025.findings-acl.700",
pages = "13623--13639",
ISBN = "979-8-89176-256-5",
abstract = "Large Language Models (LLMs) are increasingly adopted across real-world applications, yet traditional evaluations rely on expensive, domain-specific ground-truth labels that are often unavailable or infeasible. We introduce a ground-truth-free evaluation framework focused on reasoning consistency and instruction following, shifting the emphasis from correctness{---}which is elusive without labels{---}to transparent, coherent, evidence-based reasoning. Each model response must include a direct answer, a structured multi-step explanation, and supporting evidence, all assessed via semantic similarity and output adherence checks. We further propose TopK-ReRank, which refines rankings by constructing a consensus answer from the most reliable models, reducing ambiguity across diverse reasoning styles. Experiments show that our framework outperforms existing label-free methods, including majority voting, triplet ranking, and peer-review approaches, providing a more interpretable and efficient alternative for evaluating LLMs in the absence of ground-truth labels."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-reasonerrank">
<titleInfo>
<title>ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiamu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="given">Anh</namePart>
<namePart type="given">Duy</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Neng</namePart>
<namePart type="family">Chuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soo-Hyun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Hu</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are increasingly adopted across real-world applications, yet traditional evaluations rely on expensive, domain-specific ground-truth labels that are often unavailable or infeasible. We introduce a ground-truth-free evaluation framework focused on reasoning consistency and instruction following, shifting the emphasis from correctness—which is elusive without labels—to transparent, coherent, evidence-based reasoning. Each model response must include a direct answer, a structured multi-step explanation, and supporting evidence, all assessed via semantic similarity and output adherence checks. We further propose TopK-ReRank, which refines rankings by constructing a consensus answer from the most reliable models, reducing ambiguity across diverse reasoning styles. Experiments show that our framework outperforms existing label-free methods, including majority voting, triplet ranking, and peer-review approaches, providing a more interpretable and efficient alternative for evaluating LLMs in the absence of ground-truth labels.</abstract>
<identifier type="citekey">zhang-etal-2025-reasonerrank</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.700</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.700/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>13623</start>
<end>13639</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks
%A Zhang, Jiamu
%A Yuan, Jiayi
%A Wen, Andrew
%A Le, Hoang Anh Duy
%A Chuang, Yu-Neng
%A Choi, Soo-Hyun
%A Chen, Rui
%A Hu, Xia
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhang-etal-2025-reasonerrank
%X Large Language Models (LLMs) are increasingly adopted across real-world applications, yet traditional evaluations rely on expensive, domain-specific ground-truth labels that are often unavailable or infeasible. We introduce a ground-truth-free evaluation framework focused on reasoning consistency and instruction following, shifting the emphasis from correctness—which is elusive without labels—to transparent, coherent, evidence-based reasoning. Each model response must include a direct answer, a structured multi-step explanation, and supporting evidence, all assessed via semantic similarity and output adherence checks. We further propose TopK-ReRank, which refines rankings by constructing a consensus answer from the most reliable models, reducing ambiguity across diverse reasoning styles. Experiments show that our framework outperforms existing label-free methods, including majority voting, triplet ranking, and peer-review approaches, providing a more interpretable and efficient alternative for evaluating LLMs in the absence of ground-truth labels.
%R 10.18653/v1/2025.findings-acl.700
%U https://aclanthology.org/2025.findings-acl.700/
%U https://doi.org/10.18653/v1/2025.findings-acl.700
%P 13623-13639
Markdown (Informal)
[ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks](https://aclanthology.org/2025.findings-acl.700/) (Zhang et al., Findings 2025)
ACL
- Jiamu Zhang, Jiayi Yuan, Andrew Wen, Hoang Anh Duy Le, Yu-Neng Chuang, Soo-Hyun Choi, Rui Chen, and Xia Hu. 2025. ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks. In Findings of the Association for Computational Linguistics: ACL 2025, pages 13623–13639, Vienna, Austria. Association for Computational Linguistics.