<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2026-toward">
    <titleInfo>
        <title>Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Meiqing</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liam</namePart>
        <namePart type="family">Dugan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Callison-Burch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Practicing conversations with large language models (LLMs) presents a promising alternative to traditional in-person language learning. However, most LLMs generate text at a near-native level of complexity, making them ill-suited for beginner learners (CEFR: A1–A2). In this paper, we investigate whether controllable generation techniques can adapt LLM outputs to better support absolute beginners. We evaluate these methods through both automatic metrics and a user study with university-level learners of Japanese. Our findings show that while prompting alone fails, controllable generation techniques can successfully improve output comprehensibility for beginner speakers (from 39.4% to 83.3%). We further introduce a new token-level evaluation metric, Token Miss Rate (TMR), that quantifies the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments. To support future research in AI-assisted language learning, we release our code, models, annotation tools, and dataset.</abstract>
    <identifier type="citekey">jin-etal-2026-toward</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.47/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>913</start>
            <end>936</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation
%A Jin, Meiqing
%A Dugan, Liam
%A Callison-Burch, Chris
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F jin-etal-2026-toward
%X Practicing conversations with large language models (LLMs) presents a promising alternative to traditional in-person language learning. However, most LLMs generate text at a near-native level of complexity, making them ill-suited for beginner learners (CEFR: A1–A2). In this paper, we investigate whether controllable generation techniques can adapt LLM outputs to better support absolute beginners. We evaluate these methods through both automatic metrics and a user study with university-level learners of Japanese. Our findings show that while prompting alone fails, controllable generation techniques can successfully improve output comprehensibility for beginner speakers (from 39.4% to 83.3%). We further introduce a new token-level evaluation metric, Token Miss Rate (TMR), that quantifies the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments. To support future research in AI-assisted language learning, we release our code, models, annotation tools, and dataset.
%U https://aclanthology.org/2026.findings-eacl.47/
%P 913-936

Markdown (Informal)

[Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation](https://aclanthology.org/2026.findings-eacl.47/) (Jin et al., Findings 2026)

• Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation (Jin et al., Findings 2026)

ACL

• Meiqing Jin, Liam Dugan, and Chris Callison-Burch. 2026. Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation. In Findings of the Association for Computational Linguistics: EACL 2026, pages 913–936, Rabat, Morocco. Association for Computational Linguistics.