<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kadam-ferraro-2025-tag">
    <titleInfo>
        <title>TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maithili</namePart>
        <namePart type="given">Sanjay</namePart>
        <namePart type="family">Kadam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Francis</namePart>
        <namePart type="family">Ferraro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lea</namePart>
            <namePart type="family">Frermann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mark</namePart>
            <namePart type="family">Stevenson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-340-1</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) excel at general language tasks but often struggle with event-based questions—especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by ~5% on average over text-only baselines, with gains up to ~12% in zero-shot settings and ~18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.</abstract>
    <identifier type="citekey">kadam-ferraro-2025-tag</identifier>
    <location>
        <url>https://aclanthology.org/2025.starsem-1.24/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>304</start>
            <end>315</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies
%A Kadam, Maithili Sanjay
%A Ferraro, Francis
%Y Frermann, Lea
%Y Stevenson, Mark
%S Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-340-1
%F kadam-ferraro-2025-tag
%X Large language models (LLMs) excel at general language tasks but often struggle with event-based questions—especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by ~5% on average over text-only baselines, with gains up to ~12% in zero-shot settings and ~18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.
%U https://aclanthology.org/2025.starsem-1.24/
%P 304-315

Markdown (Informal)

[TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies](https://aclanthology.org/2025.starsem-1.24/) (Kadam & Ferraro, *SEM 2025)

• TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies (Kadam & Ferraro, *SEM 2025)

ACL

• Maithili Sanjay Kadam and Francis Ferraro. 2025. TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies. In Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025), pages 304–315, Suzhou, China. Association for Computational Linguistics.