<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meadows-etal-2024-exploring">
    <titleInfo>
        <title>Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="family">Meadows</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tamsin</namePart>
        <namePart type="family">James</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andre</namePart>
        <namePart type="family">Freitas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language models (LMs) can hallucinate when performing complex mathematical reasoning. Physics provides a rich domain for assessing their mathematical capabilities, where physical context requires that any symbolic manipulation satisfies complex semantics (e.g., units, tensorial order). In this work, we systematically remove crucial context from prompts to force instances where model inference may be algebraically coherent, yet unphysical. We assess LM capabilities in this domain using a curated dataset encompassing multiple notations and Physics subdomains. Further, we improve zero-shot scores using synthetic in-context examples, and demonstrate non-linear degradation of derivation quality with perturbation strength via the progressive omission of supporting premises. We find that the models’ mathematical reasoning is not physics-informed in this setting, where physical context is predominantly ignored in favour of reverse-engineering solutions.</abstract>
    <identifier type="citekey">meadows-etal-2024-exploring</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.378</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>6487</start>
            <end>6502</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
%A Meadows, Jordan
%A James, Tamsin
%A Freitas, Andre
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F meadows-etal-2024-exploring
%X Language models (LMs) can hallucinate when performing complex mathematical reasoning. Physics provides a rich domain for assessing their mathematical capabilities, where physical context requires that any symbolic manipulation satisfies complex semantics (e.g., units, tensorial order). In this work, we systematically remove crucial context from prompts to force instances where model inference may be algebraically coherent, yet unphysical. We assess LM capabilities in this domain using a curated dataset encompassing multiple notations and Physics subdomains. Further, we improve zero-shot scores using synthetic in-context examples, and demonstrate non-linear degradation of derivation quality with perturbation strength via the progressive omission of supporting premises. We find that the models’ mathematical reasoning is not physics-informed in this setting, where physical context is predominantly ignored in favour of reverse-engineering solutions.
%U https://aclanthology.org/2024.findings-emnlp.378
%P 6487-6502

Markdown (Informal)

[Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions](https://aclanthology.org/2024.findings-emnlp.378) (Meadows et al., Findings 2024)

• Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions (Meadows et al., Findings 2024)

ACL

• Jordan Meadows, Tamsin James, and Andre Freitas. 2024. Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6487–6502, Miami, Florida, USA. Association for Computational Linguistics.