<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chekin-etal-2026-building">
    <titleInfo>
        <title>Building Interpretable Feature Representations for Resume–Vacancy Matching by Distilling Production LLM Signals</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ilya</namePart>
        <namePart type="family">Chekin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vyacheslav</namePart>
        <namePart type="family">Malyugin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chirkov</namePart>
        <namePart type="family">Vladimir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikhail</namePart>
        <namePart type="family">Yurushkin</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Matching candidates to vacancies is central to recruitment, and a recruiter needs to see why a candidate fits, not only a single opaque relevance score. We provide this evidence as named, interpretable matching dimensions recruiters can act on — eight in our current deployment. We propose a two-part approach. The first is an LLM-based labeler whose prompts and feature definitions were refined from recruiter feedback while it served as an earlier production matching stage. In the current architecture, it is used only for offline labeling and is not called on online requests. The second is a feature bi-encoder distilled from it: a LoRAadapted embedding backbone with compact per-dimension heads that runs on CPU and serves all online requests. Both parts keep improving: prompts are revised as feedback arrives, and the bi-encoder is retrained on the updated labels. The model is trained on 168,772 labeled vacancy–resume pairs (17,921 vacancies and 180,030 resumes). Recruiters using the service can confirm or revise surfaced feature predictions. On 927 recruiter-recorded values from this selected production-feedback subset, the deployed student agrees with the recorded decisions in 888 cases (95.79%). This is operational, non-blinded agreement rather than an independent human evaluation.</abstract>
    <identifier type="citekey">chekin-etal-2026-building</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.71/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1209</start>
            <end>1221</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Building Interpretable Feature Representations for Resume–Vacancy Matching by Distilling Production LLM Signals
%A Chekin, Ilya
%A Malyugin, Vyacheslav
%A Vladimir, Chirkov
%A Yurushkin, Mikhail
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F chekin-etal-2026-building
%X Matching candidates to vacancies is central to recruitment, and a recruiter needs to see why a candidate fits, not only a single opaque relevance score. We provide this evidence as named, interpretable matching dimensions recruiters can act on — eight in our current deployment. We propose a two-part approach. The first is an LLM-based labeler whose prompts and feature definitions were refined from recruiter feedback while it served as an earlier production matching stage. In the current architecture, it is used only for offline labeling and is not called on online requests. The second is a feature bi-encoder distilled from it: a LoRAadapted embedding backbone with compact per-dimension heads that runs on CPU and serves all online requests. Both parts keep improving: prompts are revised as feedback arrives, and the bi-encoder is retrained on the updated labels. The model is trained on 168,772 labeled vacancy–resume pairs (17,921 vacancies and 180,030 resumes). Recruiters using the service can confirm or revise surfaced feature predictions. On 927 recruiter-recorded values from this selected production-feedback subset, the deployed student agrees with the recorded decisions in 888 cases (95.79%). This is operational, non-blinded agreement rather than an independent human evaluation.
%U https://aclanthology.org/2026.emnlp-industry.71/
%P 1209-1221

Markdown (Informal)

[Building Interpretable Feature Representations for Resume–Vacancy Matching by Distilling Production LLM Signals](https://aclanthology.org/2026.emnlp-industry.71/) (Chekin et al., EMNLP 2026)

• Building Interpretable Feature Representations for Resume–Vacancy Matching by Distilling Production LLM Signals (Chekin et al., EMNLP 2026)

ACL

• Ilya Chekin, Vyacheslav Malyugin, Chirkov Vladimir, and Mikhail Yurushkin. 2026. Building Interpretable Feature Representations for Resume–Vacancy Matching by Distilling Production LLM Signals. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1209–1221, Budapest, Hungary. Association for Computational Linguistics.