@inproceedings{wang-etal-2026-findings,
title = "Findings of the First {G}round{LM} Shared Tasks: Evaluating Grounded Language Models Across Visual and Scientific Evidence",
author = "Wang, Yimu and
Azadani, Mozhgan Nasr and
Liu, Xuye and
Choi, Yee Man and
Xue, Bo and
Czarnecki, Krzysztof",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.92/",
pages = "1232--1238",
ISBN = "979-8-89176-478-1",
abstract = "The first GroundLM shared tasks evaluate whether language models can identify the evidence behind an answer, rather than merely produce a correct answer in isolation. GoldenViewVQA requires a model to answer a multiple-choice question about six synchronized driving-camera views and identify the supporting view. LitTraceQA requires systems to retrieve scientific papers, locate answer-bearing evidence, and return multiple-choice or structured-table answers. We summarize the task design, submitted systems, official results, and recurrent failure modes. Among teams that submitted system reports, the best official joint accuracy on GoldenViewVQA is 0.8814. Answer accuracy is consistently higher than view accuracy, while macro view accuracy remains lower than micro accuracy, exposing both attribution errors and view imbalance. On the required LitTraceQA test set, the best score among teams that submitted system reports is 0.8002. Paper retrieval approaches saturation for several systems, but evidence F1 and structured-table accuracy remain substantially lower. Across both tasks, the central finding is consistent: producing a correct answer is easier than recovering the exact evidence representation required to justify it. We also report an optional 4,901-question LitTraceQA diagnostic split, whose unverified labels make it useful for stress testing but not for ranking systems on the main task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-findings">
<titleInfo>
<title>Findings of the First GroundLM Shared Tasks: Evaluating Grounded Language Models Across Visual and Scientific Evidence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuye</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Czarnecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>The first GroundLM shared tasks evaluate whether language models can identify the evidence behind an answer, rather than merely produce a correct answer in isolation. GoldenViewVQA requires a model to answer a multiple-choice question about six synchronized driving-camera views and identify the supporting view. LitTraceQA requires systems to retrieve scientific papers, locate answer-bearing evidence, and return multiple-choice or structured-table answers. We summarize the task design, submitted systems, official results, and recurrent failure modes. Among teams that submitted system reports, the best official joint accuracy on GoldenViewVQA is 0.8814. Answer accuracy is consistently higher than view accuracy, while macro view accuracy remains lower than micro accuracy, exposing both attribution errors and view imbalance. On the required LitTraceQA test set, the best score among teams that submitted system reports is 0.8002. Paper retrieval approaches saturation for several systems, but evidence F1 and structured-table accuracy remain substantially lower. Across both tasks, the central finding is consistent: producing a correct answer is easier than recovering the exact evidence representation required to justify it. We also report an optional 4,901-question LitTraceQA diagnostic split, whose unverified labels make it useful for stress testing but not for ranking systems on the main task.</abstract>
<identifier type="citekey">wang-etal-2026-findings</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.92/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1232</start>
<end>1238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the First GroundLM Shared Tasks: Evaluating Grounded Language Models Across Visual and Scientific Evidence
%A Wang, Yimu
%A Azadani, Mozhgan Nasr
%A Liu, Xuye
%A Choi, Yee Man
%A Xue, Bo
%A Czarnecki, Krzysztof
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F wang-etal-2026-findings
%X The first GroundLM shared tasks evaluate whether language models can identify the evidence behind an answer, rather than merely produce a correct answer in isolation. GoldenViewVQA requires a model to answer a multiple-choice question about six synchronized driving-camera views and identify the supporting view. LitTraceQA requires systems to retrieve scientific papers, locate answer-bearing evidence, and return multiple-choice or structured-table answers. We summarize the task design, submitted systems, official results, and recurrent failure modes. Among teams that submitted system reports, the best official joint accuracy on GoldenViewVQA is 0.8814. Answer accuracy is consistently higher than view accuracy, while macro view accuracy remains lower than micro accuracy, exposing both attribution errors and view imbalance. On the required LitTraceQA test set, the best score among teams that submitted system reports is 0.8002. Paper retrieval approaches saturation for several systems, but evidence F1 and structured-table accuracy remain substantially lower. Across both tasks, the central finding is consistent: producing a correct answer is easier than recovering the exact evidence representation required to justify it. We also report an optional 4,901-question LitTraceQA diagnostic split, whose unverified labels make it useful for stress testing but not for ranking systems on the main task.
%U https://aclanthology.org/2026.groundlm-1.92/
%P 1232-1238
Markdown (Informal)
[Findings of the First GroundLM Shared Tasks: Evaluating Grounded Language Models Across Visual and Scientific Evidence](https://aclanthology.org/2026.groundlm-1.92/) (Wang et al., GroundLM 2026)
ACL