<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-uzzi-2026-inventive">
    <titleInfo>
        <title>Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Uzzi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Large language models are increasingly used in inventive problem-solving, but effective support requires more than open-ended idea generation. Inventive problem-solving requires improving one aspect of a technical system without unintentionally worsening another. TRIZ (Theory of Inventive Problem Solving) provides a unique and structured framework for this setting by representing engineering trade-offs as contradictions and linking them to standardized inventive principles. However, prior TRIZ–LLM evaluations are typically small-scale, case studies in focused areas of technology, and rarely grounded in patent text, which makes it difficult to assess structured reasoning at scale. We introduce TRIZBench, a dataset and benchmark for TRIZ reasoning grounded in open technical sources and U.S. patents. TRIZBench evaluates the core TRIZ workflow through three tasks: contradiction prediction, inventive principle prediction, and grounded TRIZ reasoning. Experiments with multiple LLM baselines show that detecting contradictions is easier than recovering correct trade-off pairs, while principle prediction benefits from explicitly exploiting TRIZ structure. Our findings further underscore the importance of grounding. We show that semantic retrieval enables evidence-based justifications and helps explain why LLMs fail. Dataset and code are available at https://github.com/ellenzhuwang/trizbench.</abstract>
    <identifier type="citekey">wang-uzzi-2026-inventive</identifier>
    <identifier type="doi">10.18653/v1/2026.findings-acl.1798</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1798/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>36084</start>
            <end>36101</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning
%A Wang, Zhu
%A Uzzi, Brian
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-uzzi-2026-inventive
%X Large language models are increasingly used in inventive problem-solving, but effective support requires more than open-ended idea generation. Inventive problem-solving requires improving one aspect of a technical system without unintentionally worsening another. TRIZ (Theory of Inventive Problem Solving) provides a unique and structured framework for this setting by representing engineering trade-offs as contradictions and linking them to standardized inventive principles. However, prior TRIZ–LLM evaluations are typically small-scale, case studies in focused areas of technology, and rarely grounded in patent text, which makes it difficult to assess structured reasoning at scale. We introduce TRIZBench, a dataset and benchmark for TRIZ reasoning grounded in open technical sources and U.S. patents. TRIZBench evaluates the core TRIZ workflow through three tasks: contradiction prediction, inventive principle prediction, and grounded TRIZ reasoning. Experiments with multiple LLM baselines show that detecting contradictions is easier than recovering correct trade-off pairs, while principle prediction benefits from explicitly exploiting TRIZ structure. Our findings further underscore the importance of grounding. We show that semantic retrieval enables evidence-based justifications and helps explain why LLMs fail. Dataset and code are available at https://github.com/ellenzhuwang/trizbench.
%R 10.18653/v1/2026.findings-acl.1798
%U https://aclanthology.org/2026.findings-acl.1798/
%U https://doi.org/10.18653/v1/2026.findings-acl.1798
%P 36084-36101

Markdown (Informal)

[Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning](https://aclanthology.org/2026.findings-acl.1798/) (Wang & Uzzi, Findings 2026)

• Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning (Wang & Uzzi, Findings 2026)

ACL

• Zhu Wang and Brian Uzzi. 2026. Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 36084–36101, San Diego, California, United States. Association for Computational Linguistics.