<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fane-etal-2025-fane">
    <titleInfo>
        <title>Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Enfa</namePart>
        <namePart type="family">Fane</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mihai</namePart>
        <namePart type="family">Surdeanu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eduardo</namePart>
        <namePart type="family">Blanco</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steven</namePart>
        <namePart type="family">Corman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Rosenthal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aiala</namePart>
            <namePart type="family">Rosá</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-273-2</identifier>
    </relatedItem>
    <abstract>Understanding how news narratives frame entities is crucial for studying media’s impact on societal perceptions of events. In this paper, we evaluate the zero-shot capabilities of large language models (LLMs) in classifying framing roles. Through systematic experimentation, we assess the effects of input context, prompting strategies, and task decomposition. Our findings show that a hierarchical approach of first identifying broad roles and then fine-grained roles, outperforms single-step classification. We also demonstrate that optimal input contexts and prompts vary across task levels, highlighting the need for subtask-specific strategies. We achieve a Main Role Accuracy of 89.4% and an Exact Match Ratio of 34.5%, demonstrating the effectiveness of our approach. Our findings emphasize the importance of tailored prompt design and input context optimization for improving LLM performance in entity framing.</abstract>
    <identifier type="citekey">fane-etal-2025-fane</identifier>
    <location>
        <url>https://aclanthology.org/2025.semeval-1.251/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1924</start>
            <end>1934</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models
%A Fane, Enfa
%A Surdeanu, Mihai
%A Blanco, Eduardo
%A Corman, Steven
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F fane-etal-2025-fane
%X Understanding how news narratives frame entities is crucial for studying media’s impact on societal perceptions of events. In this paper, we evaluate the zero-shot capabilities of large language models (LLMs) in classifying framing roles. Through systematic experimentation, we assess the effects of input context, prompting strategies, and task decomposition. Our findings show that a hierarchical approach of first identifying broad roles and then fine-grained roles, outperforms single-step classification. We also demonstrate that optimal input contexts and prompts vary across task levels, highlighting the need for subtask-specific strategies. We achieve a Main Role Accuracy of 89.4% and an Exact Match Ratio of 34.5%, demonstrating the effectiveness of our approach. Our findings emphasize the importance of tailored prompt design and input context optimization for improving LLM performance in entity framing.
%U https://aclanthology.org/2025.semeval-1.251/
%P 1924-1934

Markdown (Informal)

[Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models](https://aclanthology.org/2025.semeval-1.251/) (Fane et al., SemEval 2025)

• Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models (Fane et al., SemEval 2025)

ACL

• Enfa Fane, Mihai Surdeanu, Eduardo Blanco, and Steven Corman. 2025. Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1924–1934, Vienna, Austria. Association for Computational Linguistics.