<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mizrahi-etal-2026-cooking">
    <titleInfo>
        <title>🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Moran</namePart>
        <namePart type="family">Mizrahi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Shani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gabriel</namePart>
        <namePart type="family">Stanovsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Jurafsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dafna</namePart>
        <namePart type="family">Shahaf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCover, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.</abstract>
    <identifier type="citekey">mizrahi-etal-2026-cooking</identifier>
    <identifier type="doi">10.1162/tacl.a.638</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.20/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>418</start>
            <end>441</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T 🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
%A Mizrahi, Moran
%A Shani, Chen
%A Stanovsky, Gabriel
%A Jurafsky, Dan
%A Shahaf, Dafna
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F mizrahi-etal-2026-cooking
%X Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCover, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.
%R 10.1162/tacl.a.638
%U https://aclanthology.org/2026.tacl-1.20/
%U https://doi.org/10.1162/tacl.a.638
%P 418-441

Markdown (Informal)

[🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination](https://aclanthology.org/2026.tacl-1.20/) (Mizrahi et al., TACL 2026)

• 🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination (Mizrahi et al., TACL 2026)

ACL

• Moran Mizrahi, Chen Shani, Gabriel Stanovsky, Dan Jurafsky, and Dafna Shahaf. 2026. 🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination. Transactions of the Association for Computational Linguistics, 14:418–441.