<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fisher-etal-2026-response">
    <titleInfo>
        <title>Response-Aware User Memory Selection for LLM Personalization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jillian</namePart>
        <namePart type="family">Fisher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jennifer</namePart>
        <namePart type="family">Neville</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chan</namePart>
        <namePart type="given">Young</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model’s generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect the model’s response distribution. We propose **R**esponse-**U**tility optimization for **M**emory **S**election (RUMS), a novel method that selects user memory items by measuring the mutual information between a subset of memory and the model’s outputs, identifying items that reduce response uncertainty and sharpen predictions beyond semantic similarity. We demonstrate that this information-theoretic foundation enables more principled user memory selection that aligns more closely with human selection compared to state-of-the-art methods, and models that are 400 \times larger. Additionally, we show that memory items selected using RUMS result in better response quality compared to existing approaches, while having up to 95% reduction in computational cost.</abstract>
    <identifier type="citekey">fisher-etal-2026-response</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.185/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4215</start>
            <end>4267</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Response-Aware User Memory Selection for LLM Personalization
%A Fisher, Jillian
%A Neville, Jennifer
%A Park, Chan Young
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F fisher-etal-2026-response
%X A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model’s generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect the model’s response distribution. We propose **R**esponse-**U**tility optimization for **M**emory **S**election (RUMS), a novel method that selects user memory items by measuring the mutual information between a subset of memory and the model’s outputs, identifying items that reduce response uncertainty and sharpen predictions beyond semantic similarity. We demonstrate that this information-theoretic foundation enables more principled user memory selection that aligns more closely with human selection compared to state-of-the-art methods, and models that are 400 \times larger. Additionally, we show that memory items selected using RUMS result in better response quality compared to existing approaches, while having up to 95% reduction in computational cost.
%U https://aclanthology.org/2026.emnlp-main.185/
%P 4215-4267

Markdown (Informal)

[Response-Aware User Memory Selection for LLM Personalization](https://aclanthology.org/2026.emnlp-main.185/) (Fisher et al., EMNLP 2026)

• Response-Aware User Memory Selection for LLM Personalization (Fisher et al., EMNLP 2026)

ACL

• Jillian Fisher, Jennifer Neville, and Chan Young Park. 2026. Response-Aware User Memory Selection for LLM Personalization. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 4215–4267, Budapest, Hungary. Association for Computational Linguistics.