<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-llm-fine">
    <titleInfo>
        <title>LLM Fine-tuning with an Unconstrained Fine-tuned Teacher</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jianhao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ou</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Du</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>Fine-tuning large language models (LLMs) on a single target task requires balancing task adaptation with retention of prior capabilities. Existing teachers mainly guide preservation or transfer, but do not identify which target-task samples should be emphasized when fine-tuning must retain prior capabilities. We propose the **U**nconstrained **F**ine-tuned **T**eacher (**UFT**), shifting the teacher role from “knowledge transfer” to “value discovery”. UFT is obtained by unconstrained fine-tuning on the target task and then compared with the source model to identify high-value samples. These samples are upweighted during student fine-tuning and receive value-weighted UFT-guided distillation, allowing the student to prioritize task-critical signals while preserving prior capabilities. Experiments on Magicoder and MetaMathQA show that UFT improves the trade-off between target-task performance and prior-capability retention, while converging faster and more stably. By turning teacher behavior into sample-value discovery, UFT establishes a new teacher role for data-efficient fine-tuning.</abstract>
    <identifier type="citekey">zhang-etal-2026-llm-fine</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1310/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>29812</start>
            <end>29839</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLM Fine-tuning with an Unconstrained Fine-tuned Teacher
%A Zhang, Jianhao
%A Wu, Ou
%A Du, Yi
%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 zhang-etal-2026-llm-fine
%X Fine-tuning large language models (LLMs) on a single target task requires balancing task adaptation with retention of prior capabilities. Existing teachers mainly guide preservation or transfer, but do not identify which target-task samples should be emphasized when fine-tuning must retain prior capabilities. We propose the **U**nconstrained **F**ine-tuned **T**eacher (**UFT**), shifting the teacher role from “knowledge transfer” to “value discovery”. UFT is obtained by unconstrained fine-tuning on the target task and then compared with the source model to identify high-value samples. These samples are upweighted during student fine-tuning and receive value-weighted UFT-guided distillation, allowing the student to prioritize task-critical signals while preserving prior capabilities. Experiments on Magicoder and MetaMathQA show that UFT improves the trade-off between target-task performance and prior-capability retention, while converging faster and more stably. By turning teacher behavior into sample-value discovery, UFT establishes a new teacher role for data-efficient fine-tuning.
%U https://aclanthology.org/2026.emnlp-main.1310/
%P 29812-29839

Markdown (Informal)

[LLM Fine-tuning with an Unconstrained Fine-tuned Teacher](https://aclanthology.org/2026.emnlp-main.1310/) (Zhang et al., EMNLP 2026)

• LLM Fine-tuning with an Unconstrained Fine-tuned Teacher (Zhang et al., EMNLP 2026)

ACL

• Jianhao Zhang, Ou Wu, and Yi Du. 2026. LLM Fine-tuning with an Unconstrained Fine-tuned Teacher. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 29812–29839, Budapest, Hungary. Association for Computational Linguistics.