@inproceedings{kaur-etal-2026-adapting,
title = "Adapting {A}uto{ARGUE} for Automatic Report Evaluation under Missing Citation Annotations",
author = "Kaur, Divrose and
Bedi, Jatin and
Singh, Jasmeet",
editor = "Yang, Eugene and
Lawrie, Dawn and
MacAvaney, Sean and
Mayfield, James and
Soldaini, Luca and
Yates, Andrew",
booktitle = "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation ({RAG}4{R}eports 2026)",
month = jul,
year = "2026",
address = "San Diego, CA, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.rag4reports-1.15/",
pages = "103--107",
ISBN = "979-8-89176-417-0",
abstract = "We adapt the AutoARGUE framework (Walden et al., 2026) for Task A.2 of RAG4Reports 2026, which requires ranking 57 report generation systems across 68 topics using automated evaluation. The RAGTIME-1 corpus poses a fundamental challenge: all nugget annotations use a no-reference-doc sentinel rather than ground-truth document citations, rendering the original citation-relevance gating inoperable. We address this with three adaptations: automatic sentinel detection with forced direct LLM-based nugget matching; a WEAK POSITIVE partial credit mechanism for sentences that correctly answer nuggets but lack attesting citations; and a report-level request alignment check. Our nugget{\_}coverage{\_}weighted metric achieves the highest topic-level Pearson correlation (r=0.599) of any non-coordinator submission, closely approaching the coordinator baseline (r=0.607)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaur-etal-2026-adapting">
<titleInfo>
<title>Adapting AutoARGUE for Automatic Report Evaluation under Missing Citation Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divrose</namePart>
<namePart type="family">Kaur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Bedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasmeet</namePart>
<namePart type="family">Singh</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 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Lawrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Mayfield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Soldaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, CA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-417-0</identifier>
</relatedItem>
<abstract>We adapt the AutoARGUE framework (Walden et al., 2026) for Task A.2 of RAG4Reports 2026, which requires ranking 57 report generation systems across 68 topics using automated evaluation. The RAGTIME-1 corpus poses a fundamental challenge: all nugget annotations use a no-reference-doc sentinel rather than ground-truth document citations, rendering the original citation-relevance gating inoperable. We address this with three adaptations: automatic sentinel detection with forced direct LLM-based nugget matching; a WEAK POSITIVE partial credit mechanism for sentences that correctly answer nuggets but lack attesting citations; and a report-level request alignment check. Our nugget_coverage_weighted metric achieves the highest topic-level Pearson correlation (r=0.599) of any non-coordinator submission, closely approaching the coordinator baseline (r=0.607).</abstract>
<identifier type="citekey">kaur-etal-2026-adapting</identifier>
<location>
<url>https://aclanthology.org/2026.rag4reports-1.15/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>103</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting AutoARGUE for Automatic Report Evaluation under Missing Citation Annotations
%A Kaur, Divrose
%A Bedi, Jatin
%A Singh, Jasmeet
%Y Yang, Eugene
%Y Lawrie, Dawn
%Y MacAvaney, Sean
%Y Mayfield, James
%Y Soldaini, Luca
%Y Yates, Andrew
%S Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA, USA
%@ 979-8-89176-417-0
%F kaur-etal-2026-adapting
%X We adapt the AutoARGUE framework (Walden et al., 2026) for Task A.2 of RAG4Reports 2026, which requires ranking 57 report generation systems across 68 topics using automated evaluation. The RAGTIME-1 corpus poses a fundamental challenge: all nugget annotations use a no-reference-doc sentinel rather than ground-truth document citations, rendering the original citation-relevance gating inoperable. We address this with three adaptations: automatic sentinel detection with forced direct LLM-based nugget matching; a WEAK POSITIVE partial credit mechanism for sentences that correctly answer nuggets but lack attesting citations; and a report-level request alignment check. Our nugget_coverage_weighted metric achieves the highest topic-level Pearson correlation (r=0.599) of any non-coordinator submission, closely approaching the coordinator baseline (r=0.607).
%U https://aclanthology.org/2026.rag4reports-1.15/
%P 103-107
Markdown (Informal)
[Adapting AutoARGUE for Automatic Report Evaluation under Missing Citation Annotations](https://aclanthology.org/2026.rag4reports-1.15/) (Kaur et al., RAG4Reports 2026)
ACL