<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahmani-vertanen-2026-improved">
    <titleInfo>
        <title>Improved Personalized Typing Predictions via Long Left Context</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soufia</namePart>
        <namePart type="family">Bahmani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keith</namePart>
        <namePart type="family">Vertanen</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 10th Widening NLP Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chen</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Allaway</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Meryem</namePart>
            <namePart type="family">M’hamdi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peerat</namePart>
            <namePart type="family">Limkonchotiwat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="given">He</namePart>
            <namePart type="family">Bai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yinqiao</namePart>
            <namePart type="family">Li</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">979-8-89176-472-9</identifier>
    </relatedItem>
    <abstract>We study how to improve predictive typing via per-user personalization of a pretrained large language model (LLM). We evaluate personalization in a time-ordered setting, using each user’s earlier messages for adaptation as we try to predict their next message. We compare: (1) personalization versus a non-personalized base model, (2) differing amounts of left context, (3) one-time adaptation versus making small periodic updates, and (4) full fine-tuning versus parameter-efficient fine-tuning. We find both static and personalized LLMs significantly outperform an n-gram language model. This includes when the n-gram was mixed with a user model learned via prediction by partial matching (PPM). Using long recent user-specific context provided the largest personalization gains: conditioning on up to 1024 previous characters reduced the base model’s perplexity by 18%. We found fine-tuning model weights provided only a small additional gain.</abstract>
    <identifier type="citekey">bahmani-vertanen-2026-improved</identifier>
    <location>
        <url>https://aclanthology.org/2026.winlp-main.11/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>105</start>
            <end>120</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improved Personalized Typing Predictions via Long Left Context
%A Bahmani, Soufia
%A Vertanen, Keith
%Y Zhang, Chen
%Y Allaway, Emily
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.Y.S.S., Santosh
%Y Thapa, Surendrabikram
%Y Li, Yinqiao
%S Proceedings of the 10th Widening NLP Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-472-9
%F bahmani-vertanen-2026-improved
%X We study how to improve predictive typing via per-user personalization of a pretrained large language model (LLM). We evaluate personalization in a time-ordered setting, using each user’s earlier messages for adaptation as we try to predict their next message. We compare: (1) personalization versus a non-personalized base model, (2) differing amounts of left context, (3) one-time adaptation versus making small periodic updates, and (4) full fine-tuning versus parameter-efficient fine-tuning. We find both static and personalized LLMs significantly outperform an n-gram language model. This includes when the n-gram was mixed with a user model learned via prediction by partial matching (PPM). Using long recent user-specific context provided the largest personalization gains: conditioning on up to 1024 previous characters reduced the base model’s perplexity by 18%. We found fine-tuning model weights provided only a small additional gain.
%U https://aclanthology.org/2026.winlp-main.11/
%P 105-120

Markdown (Informal)

[Improved Personalized Typing Predictions via Long Left Context](https://aclanthology.org/2026.winlp-main.11/) (Bahmani & Vertanen, WiNLP 2026)

• Improved Personalized Typing Predictions via Long Left Context (Bahmani & Vertanen, WiNLP 2026)

ACL

• Soufia Bahmani and Keith Vertanen. 2026. Improved Personalized Typing Predictions via Long Left Context. In Proceedings of the 10th Widening NLP Workshop, pages 105–120, Budapest, Hungary. Association for Computational Linguistics.