<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2026-cross">
    <titleInfo>
        <title>Cross-Decoder Retargeting of Soft Compressor for Long-Context Compression</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yanhan</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhijie</namePart>
        <namePart type="family">Nie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richong</namePart>
        <namePart type="family">Zhang</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>Soft compression stores a text span as k continuous compressed vectors for a frozen decoder, but existing compressors are usually tied to the decoder used during training. We study whether those vectors can be retargeted to a different frozen decoder through its input-embedding interface under a controlled reconstruction protocol. Our benchmark covers seven target decoders, three vector budgets, and directed source–target pairs, comparing Random, shared-embedding least squares (LS), Converter-only, Enc-Conv, and target-native Origin. Converter-only maps vectors from a frozen source compressor, whereas Enc-Conv also adapts the source-initialized vector generator. Transfer is feasible but decoder-conditioned: trainable retargeting can approach Origin BLEU on decoder-compatible targets, while LS is often close to Random despite using shared token anchors. Enc-Conv consistently matches or outperforms Converter-only, with its largest gains on difficult transfers. Selected-pair multi-seed runs and a small SQuAD probe provide complementary evidence, although downstream utility remains target-dependent. Perturbation and geometry probes are consistent with decoder-specific readable regions. Finally, pair-level readability scores provide weak-to-moderate pre-transfer screening signals.</abstract>
    <identifier type="citekey">ye-etal-2026-cross</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.373/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>8529</start>
            <end>8541</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Decoder Retargeting of Soft Compressor for Long-Context Compression
%A Ye, Yanhan
%A Nie, Zhijie
%A Zhang, Richong
%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 ye-etal-2026-cross
%X Soft compression stores a text span as k continuous compressed vectors for a frozen decoder, but existing compressors are usually tied to the decoder used during training. We study whether those vectors can be retargeted to a different frozen decoder through its input-embedding interface under a controlled reconstruction protocol. Our benchmark covers seven target decoders, three vector budgets, and directed source–target pairs, comparing Random, shared-embedding least squares (LS), Converter-only, Enc-Conv, and target-native Origin. Converter-only maps vectors from a frozen source compressor, whereas Enc-Conv also adapts the source-initialized vector generator. Transfer is feasible but decoder-conditioned: trainable retargeting can approach Origin BLEU on decoder-compatible targets, while LS is often close to Random despite using shared token anchors. Enc-Conv consistently matches or outperforms Converter-only, with its largest gains on difficult transfers. Selected-pair multi-seed runs and a small SQuAD probe provide complementary evidence, although downstream utility remains target-dependent. Perturbation and geometry probes are consistent with decoder-specific readable regions. Finally, pair-level readability scores provide weak-to-moderate pre-transfer screening signals.
%U https://aclanthology.org/2026.emnlp-main.373/
%P 8529-8541

Markdown (Informal)

[Cross-Decoder Retargeting of Soft Compressor for Long-Context Compression](https://aclanthology.org/2026.emnlp-main.373/) (Ye et al., EMNLP 2026)

• Cross-Decoder Retargeting of Soft Compressor for Long-Context Compression (Ye et al., EMNLP 2026)

ACL

• Yanhan Ye, Zhijie Nie, and Richong Zhang. 2026. Cross-Decoder Retargeting of Soft Compressor for Long-Context Compression. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 8529–8541, Budapest, Hungary. Association for Computational Linguistics.