<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coleman-krishnamachari-2026-toward">
    <titleInfo>
        <title>Toward End-to-End Open-Weight LLM-RBMT for Endangered Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jared</namePart>
        <namePart type="family">Coleman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bhaskar</namePart>
        <namePart type="family">Krishnamachari</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>We present an end-to-end open-weight pipeline for LLM-Assisted Rule-Based Machine Translation (LLM-RBMT) into extremely low-resource languages, with no proprietary-API dependency at any stage and no per-language linguistic effort beyond registering a language with the framework. On Owens Valley Paiute (OVP), a critically endangered Indigenous language of California, we synthesize training data entirely from the OVP language specification, fine-tune two Qwen2.5-3B LoRA adapters (one for each LLM-driven stage of the translation system), and serve both locally. The fine-tuned forward adapter matches or exceeds gpt-4o-mini on the 150-sentence forward evaluation of Coleman et al. (2026) (COMET-c 0.472 vs. 0.448, same evaluator), and a separately fine-tuned backward adapter approaches it on a 40-item hand-validated backward reference set, both running locally. The full recipe runs on a single consumer GPU.</abstract>
    <identifier type="citekey">coleman-krishnamachari-2026-toward</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1832/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>41703</start>
            <end>41714</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Toward End-to-End Open-Weight LLM-RBMT for Endangered Languages
%A Coleman, Jared
%A Krishnamachari, Bhaskar
%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 coleman-krishnamachari-2026-toward
%X We present an end-to-end open-weight pipeline for LLM-Assisted Rule-Based Machine Translation (LLM-RBMT) into extremely low-resource languages, with no proprietary-API dependency at any stage and no per-language linguistic effort beyond registering a language with the framework. On Owens Valley Paiute (OVP), a critically endangered Indigenous language of California, we synthesize training data entirely from the OVP language specification, fine-tune two Qwen2.5-3B LoRA adapters (one for each LLM-driven stage of the translation system), and serve both locally. The fine-tuned forward adapter matches or exceeds gpt-4o-mini on the 150-sentence forward evaluation of Coleman et al. (2026) (COMET-c 0.472 vs. 0.448, same evaluator), and a separately fine-tuned backward adapter approaches it on a 40-item hand-validated backward reference set, both running locally. The full recipe runs on a single consumer GPU.
%U https://aclanthology.org/2026.emnlp-main.1832/
%P 41703-41714

Markdown (Informal)

[Toward End-to-End Open-Weight LLM-RBMT for Endangered Languages](https://aclanthology.org/2026.emnlp-main.1832/) (Coleman & Krishnamachari, EMNLP 2026)

• Toward End-to-End Open-Weight LLM-RBMT for Endangered Languages (Coleman & Krishnamachari, EMNLP 2026)

ACL

• Jared Coleman and Bhaskar Krishnamachari. 2026. Toward End-to-End Open-Weight LLM-RBMT for Endangered Languages. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 41703–41714, Budapest, Hungary. Association for Computational Linguistics.