@inproceedings{pattnayak-bhatia-2026-reproevalcard,
title = "{R}epro{E}val{C}ard: A Reporting Standard for Reproducible Evaluation of {LLM} Pipelines",
author = "Pattnayak, Priyaranjan and
Bhatia, Apoorv",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-short.22/",
pages = "238--249",
ISBN = "979-8-89176-391-3",
abstract = "Evaluation of modern large language model (LLM) systems increasingly relies on multi-stage pipelines such as retrieval-augmented generation, tool-using agents, and prompt chains. Reproducing reported evaluation results for these systems often requires evaluation-specific artifacts beyond model weights and datasets, including prompts, judge configurations, retrieval snapshots, and intermediate traces, yet their availability has not been systematically examined.We introduce \textbf{ReproEvalCard}, a lightweight reporting standard that specifies the minimal artifacts required to reproduce and validate evaluations of LLM pipelines. To motivate this standard, we audit 55 pipeline-based LLM papers published between 2022 and 2025 and quantify the availability of reproducibility-critical evaluation artifacts. We find that randomness controls are missing in 75{\%} of papers and intermediate execution traces in 61{\%}, substantially limiting evaluation reproducibility. We further demonstrate ReproEvalCard through a worked example and provide a concise checklist for authors and reviewers, aiming to improve reproducibility and comparability in LLM evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pattnayak-bhatia-2026-reproevalcard">
<titleInfo>
<title>ReproEvalCard: A Reporting Standard for Reproducible Evaluation of LLM Pipelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priyaranjan</namePart>
<namePart type="family">Pattnayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-391-3</identifier>
</relatedItem>
<abstract>Evaluation of modern large language model (LLM) systems increasingly relies on multi-stage pipelines such as retrieval-augmented generation, tool-using agents, and prompt chains. Reproducing reported evaluation results for these systems often requires evaluation-specific artifacts beyond model weights and datasets, including prompts, judge configurations, retrieval snapshots, and intermediate traces, yet their availability has not been systematically examined.We introduce ReproEvalCard, a lightweight reporting standard that specifies the minimal artifacts required to reproduce and validate evaluations of LLM pipelines. To motivate this standard, we audit 55 pipeline-based LLM papers published between 2022 and 2025 and quantify the availability of reproducibility-critical evaluation artifacts. We find that randomness controls are missing in 75% of papers and intermediate execution traces in 61%, substantially limiting evaluation reproducibility. We further demonstrate ReproEvalCard through a worked example and provide a concise checklist for authors and reviewers, aiming to improve reproducibility and comparability in LLM evaluation.</abstract>
<identifier type="citekey">pattnayak-bhatia-2026-reproevalcard</identifier>
<location>
<url>https://aclanthology.org/2026.acl-short.22/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>238</start>
<end>249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproEvalCard: A Reporting Standard for Reproducible Evaluation of LLM Pipelines
%A Pattnayak, Priyaranjan
%A Bhatia, Apoorv
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F pattnayak-bhatia-2026-reproevalcard
%X Evaluation of modern large language model (LLM) systems increasingly relies on multi-stage pipelines such as retrieval-augmented generation, tool-using agents, and prompt chains. Reproducing reported evaluation results for these systems often requires evaluation-specific artifacts beyond model weights and datasets, including prompts, judge configurations, retrieval snapshots, and intermediate traces, yet their availability has not been systematically examined.We introduce ReproEvalCard, a lightweight reporting standard that specifies the minimal artifacts required to reproduce and validate evaluations of LLM pipelines. To motivate this standard, we audit 55 pipeline-based LLM papers published between 2022 and 2025 and quantify the availability of reproducibility-critical evaluation artifacts. We find that randomness controls are missing in 75% of papers and intermediate execution traces in 61%, substantially limiting evaluation reproducibility. We further demonstrate ReproEvalCard through a worked example and provide a concise checklist for authors and reviewers, aiming to improve reproducibility and comparability in LLM evaluation.
%U https://aclanthology.org/2026.acl-short.22/
%P 238-249
Markdown (Informal)
[ReproEvalCard: A Reporting Standard for Reproducible Evaluation of LLM Pipelines](https://aclanthology.org/2026.acl-short.22/) (Pattnayak & Bhatia, ACL 2026)
ACL