<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rai-etal-2025-injecting">
    <titleInfo>
        <title>Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shahid</namePart>
        <namePart type="given">Iqbal</namePart>
        <namePart type="family">Rai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danilo</namePart>
        <namePart type="family">Croce</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roberto</namePart>
        <namePart type="family">Basili</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) have demonstrated remarkable generalization across diverse NLP tasks, yet they often produce outputs lacking semantic coherence due to insufficient grounding in structured linguistic knowledge. This paper proposes a novel method for injecting Frame Semantics into a pretrained LLaMA model using Low-Rank Adaptation (LoRA). Leveraging FrameNet (a rich resource of over 1,000 semantic frames) we construct a training corpus comprising structured triples of frame definitions, frame elements, and lexical units. Our method encodes these examples into the model via LoRA adapters and evaluates performance using zero-shot prompting for textual entailment and semantic role labeling (SRL) over Framenet. Experimental results show that our adapted frame-aware LLM substantially outperforms the baseline across closed, open-ended, and multiple-choice prompts. Moreover, we observe significant improvements in SRL accuracy, demonstrating the efficacy of combining frame-semantic theory with parameter-efficient pretraining.</abstract>
    <identifier type="citekey">rai-etal-2025-injecting</identifier>
    <location>
        <url>https://aclanthology.org/2025.starsem-1.3/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>31</start>
            <end>47</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning
%A Rai, Shahid Iqbal
%A Croce, Danilo
%A Basili, Roberto
%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 rai-etal-2025-injecting
%X Large Language Models (LLMs) have demonstrated remarkable generalization across diverse NLP tasks, yet they often produce outputs lacking semantic coherence due to insufficient grounding in structured linguistic knowledge. This paper proposes a novel method for injecting Frame Semantics into a pretrained LLaMA model using Low-Rank Adaptation (LoRA). Leveraging FrameNet (a rich resource of over 1,000 semantic frames) we construct a training corpus comprising structured triples of frame definitions, frame elements, and lexical units. Our method encodes these examples into the model via LoRA adapters and evaluates performance using zero-shot prompting for textual entailment and semantic role labeling (SRL) over Framenet. Experimental results show that our adapted frame-aware LLM substantially outperforms the baseline across closed, open-ended, and multiple-choice prompts. Moreover, we observe significant improvements in SRL accuracy, demonstrating the efficacy of combining frame-semantic theory with parameter-efficient pretraining.
%U https://aclanthology.org/2025.starsem-1.3/
%P 31-47

Markdown (Informal)

[Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning](https://aclanthology.org/2025.starsem-1.3/) (Rai et al., *SEM 2025)

• Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning (Rai et al., *SEM 2025)

ACL

• Shahid Iqbal Rai, Danilo Croce, and Roberto Basili. 2025. Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning. In Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025), pages 31–47, Suzhou, China. Association for Computational Linguistics.