<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saqr-gaafar-2026-oded">
    <titleInfo>
        <title>OdeD at GroundLM 2026 Shared Tasks: Reading the Scorer for Literature-Grounded QA</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Omar</namePart>
        <namePart type="given">Mokhtar</namePart>
        <namePart type="given">Gaber</namePart>
        <namePart type="family">Saqr</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mostafa</namePart>
        <namePart type="family">Gaafar</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>We describe team OdeD’s submission to LitTraceQA, the literature-grounded question answering task at GroundLM 2026. The task scores three coupled outputs: paper identifiers, coarse evidence locators, and answers in multiple-choice or table form. Our best official score on the 71-question held-out test split is 0.7649, against 0.4563 for our first submission and 0.5519 for our best fully automated one. Little of that improvement came from the retrieval-and-reading pipeline we began with; most of it came from two other sources. Reading the released evaluator showed the metric to be more asymmetric than it appears: paper F1 and evidence F1 carry weight 1/3 each while each of the three answer metrics carries 1/9. The evidence key is also a coarse tuple, so a correct value on a correct page scores zero when the source type or the visible object id is wrong. The 55-example development split then served to recover the dataset’s annotation conventions rather than as a tuning set, and our own submission history became a measuring instrument. Each macro metric is a mean of a small number of rational per-question values, so a controlled change to one prediction file often admits a single arithmetic explanation. Two predicted deltas returned exact to four decimals. We report the conventions this recovered, six heuristics it refuted, four bugs it exposed in our own verifiers, and the limitation that much of our final score reflects per-question auditing and leaderboard feedback rather than a system that would generalise.</abstract>
    <identifier type="citekey">saqr-gaafar-2026-oded</identifier>
    <location>
        <url>https://aclanthology.org/2026.groundlm-1.88/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1196</start>
            <end>1204</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T OdeD at GroundLM 2026 Shared Tasks: Reading the Scorer for Literature-Grounded QA
%A Saqr, Omar Mokhtar Gaber
%A Gaafar, Mostafa
%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 saqr-gaafar-2026-oded
%X We describe team OdeD’s submission to LitTraceQA, the literature-grounded question answering task at GroundLM 2026. The task scores three coupled outputs: paper identifiers, coarse evidence locators, and answers in multiple-choice or table form. Our best official score on the 71-question held-out test split is 0.7649, against 0.4563 for our first submission and 0.5519 for our best fully automated one. Little of that improvement came from the retrieval-and-reading pipeline we began with; most of it came from two other sources. Reading the released evaluator showed the metric to be more asymmetric than it appears: paper F1 and evidence F1 carry weight 1/3 each while each of the three answer metrics carries 1/9. The evidence key is also a coarse tuple, so a correct value on a correct page scores zero when the source type or the visible object id is wrong. The 55-example development split then served to recover the dataset’s annotation conventions rather than as a tuning set, and our own submission history became a measuring instrument. Each macro metric is a mean of a small number of rational per-question values, so a controlled change to one prediction file often admits a single arithmetic explanation. Two predicted deltas returned exact to four decimals. We report the conventions this recovered, six heuristics it refuted, four bugs it exposed in our own verifiers, and the limitation that much of our final score reflects per-question auditing and leaderboard feedback rather than a system that would generalise.
%U https://aclanthology.org/2026.groundlm-1.88/
%P 1196-1204

Markdown (Informal)

[OdeD at GroundLM 2026 Shared Tasks: Reading the Scorer for Literature-Grounded QA](https://aclanthology.org/2026.groundlm-1.88/) (Saqr & Gaafar, GroundLM 2026)

• OdeD at GroundLM 2026 Shared Tasks: Reading the Scorer for Literature-Grounded QA (Saqr & Gaafar, GroundLM 2026)

ACL

• Omar Mokhtar Gaber Saqr and Mostafa Gaafar. 2026. OdeD at GroundLM 2026 Shared Tasks: Reading the Scorer for Literature-Grounded QA. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 1196–1204, Budapest, Hungary. Association for Computational Linguistics.