@inproceedings{bliss-etal-2026-concord,
title = "Concord: An Agreement-Aware Multi-Adjudication Pipeline for {LLM} Evaluation",
author = "Bliss, Tyler and
Verma, Mahit and
Iyer-Singh, Aila and
Biswas, Subrata and
Imran, Sheikh Asif and
Islam, Bashima",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.46/",
pages = "502--510",
ISBN = "979-8-89176-423-1",
abstract = "Evaluating multimodal generations is challenging: human evaluation is costly, and single-model LLM-as-a-judge pipelines can be brittle and provide limited uncertainty signals. We introduce Concord, an ensemble-based evaluation pipeline that aggregates discrete judgments from multiple LLM judges and uses inter-judge agreement as a practical uncertainty signal for disagreement-driven triage. We evaluate Concord on AVSSD and SCORE-AVS, a ground-truth-supervised audio-visual benchmark with discrete labels (True/False or 0{--}5). Concord improves agreement with human judgments over single-judge and naive aggregation baselines, and prioritizing low-agreement instances focuses human review on the most ambiguous cases. We use locally hosted open-source judges and include the binary results for online larger scale models GPT4.o mini turbo and Gemini 3.1 Flash Lite."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bliss-etal-2026-concord">
<titleInfo>
<title>Concord: An Agreement-Aware Multi-Adjudication Pipeline for LLM Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Bliss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahit</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aila</namePart>
<namePart type="family">Iyer-Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subrata</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheikh</namePart>
<namePart type="given">Asif</namePart>
<namePart type="family">Imran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashima</namePart>
<namePart type="family">Islam</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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>Evaluating multimodal generations is challenging: human evaluation is costly, and single-model LLM-as-a-judge pipelines can be brittle and provide limited uncertainty signals. We introduce Concord, an ensemble-based evaluation pipeline that aggregates discrete judgments from multiple LLM judges and uses inter-judge agreement as a practical uncertainty signal for disagreement-driven triage. We evaluate Concord on AVSSD and SCORE-AVS, a ground-truth-supervised audio-visual benchmark with discrete labels (True/False or 0–5). Concord improves agreement with human judgments over single-judge and naive aggregation baselines, and prioritizing low-agreement instances focuses human review on the most ambiguous cases. We use locally hosted open-source judges and include the binary results for online larger scale models GPT4.o mini turbo and Gemini 3.1 Flash Lite.</abstract>
<identifier type="citekey">bliss-etal-2026-concord</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.46/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>502</start>
<end>510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Concord: An Agreement-Aware Multi-Adjudication Pipeline for LLM Evaluation
%A Bliss, Tyler
%A Verma, Mahit
%A Iyer-Singh, Aila
%A Biswas, Subrata
%A Imran, Sheikh Asif
%A Islam, Bashima
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F bliss-etal-2026-concord
%X Evaluating multimodal generations is challenging: human evaluation is costly, and single-model LLM-as-a-judge pipelines can be brittle and provide limited uncertainty signals. We introduce Concord, an ensemble-based evaluation pipeline that aggregates discrete judgments from multiple LLM judges and uses inter-judge agreement as a practical uncertainty signal for disagreement-driven triage. We evaluate Concord on AVSSD and SCORE-AVS, a ground-truth-supervised audio-visual benchmark with discrete labels (True/False or 0–5). Concord improves agreement with human judgments over single-judge and naive aggregation baselines, and prioritizing low-agreement instances focuses human review on the most ambiguous cases. We use locally hosted open-source judges and include the binary results for online larger scale models GPT4.o mini turbo and Gemini 3.1 Flash Lite.
%U https://aclanthology.org/2026.gem-main.46/
%P 502-510
Markdown (Informal)
[Concord: An Agreement-Aware Multi-Adjudication Pipeline for LLM Evaluation](https://aclanthology.org/2026.gem-main.46/) (Bliss et al., GEM 2026)
ACL
- Tyler Bliss, Mahit Verma, Aila Iyer-Singh, Subrata Biswas, Sheikh Asif Imran, and Bashima Islam. 2026. Concord: An Agreement-Aware Multi-Adjudication Pipeline for LLM Evaluation. In Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM), pages 502–510, San Diego, California, USA. Association for Computational Linguistics.