<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2026-prompt">
    <titleInfo>
        <title>Prompt as Stratified Interface: Decomposing Label-Mediated Effects in Chinese-English NLI</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hua</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiqing</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michelle</namePart>
        <namePart type="given">Mingyue</namePart>
        <namePart type="family">Gu</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Leonardo</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Pucci</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Federico</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Valentino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandra</namePart>
            <namePart type="family">Birch</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabio</namePart>
            <namePart type="given">Massimo</namePart>
            <namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
    </relatedItem>
    <abstract>Multilingual prompting studies often compare English instructions with target-language instructions. For classification, however, this comparison bundles more than instruction wording: prompts also define categories, name them, bind them to answer symbols, and specify an output form. We study this label interface in Chinese-English XNLI with examples, gold labels, and decoding fixed. Under ordinary semantic-label prompting, Qwen3-8B shows large CN-interface gains on both input sides, larger Qwen3 models are near zero, and Llama3.1-70B shows a smaller gain concentrated on Chinese inputs. Removing visible category names with all six A/B/C permutations nearly eliminates the Qwen3-8B gains, while Llama-3.1-70B retains a Chinese-input residual. Restoring names inside A/B/C options improves accuracy and reduces the largest mapping instabilities, but signed contrasts remain model-specific. Direct semantic-label output adds only small gains once category names are visible. A targeted 2 × 2 follow-up associates the Llama-3.1-70B Chinese-input residual primarily with procedural-block language on average, moderated by relation-definition language; alternate-label and crossed-label checks further show that exact label wording and language can shrink or reverse the signed contrast. We use semantic label anchoring only as descriptive shorthand. The result is a scoped measurementvalidity finding for Chinese-English XNLI and the tested prompt family, not a claim of invariance across language pairs or prompt paraphrases.</abstract>
    <identifier type="citekey">zhao-etal-2026-prompt</identifier>
    <location>
        <url>https://aclanthology.org/2026.oracle-main.35/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>515</start>
            <end>533</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompt as Stratified Interface: Decomposing Label-Mediated Effects in Chinese-English NLI
%A Zhao, Hua
%A Yang, Zhiqing
%A Gu, Michelle Mingyue
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F zhao-etal-2026-prompt
%X Multilingual prompting studies often compare English instructions with target-language instructions. For classification, however, this comparison bundles more than instruction wording: prompts also define categories, name them, bind them to answer symbols, and specify an output form. We study this label interface in Chinese-English XNLI with examples, gold labels, and decoding fixed. Under ordinary semantic-label prompting, Qwen3-8B shows large CN-interface gains on both input sides, larger Qwen3 models are near zero, and Llama3.1-70B shows a smaller gain concentrated on Chinese inputs. Removing visible category names with all six A/B/C permutations nearly eliminates the Qwen3-8B gains, while Llama-3.1-70B retains a Chinese-input residual. Restoring names inside A/B/C options improves accuracy and reduces the largest mapping instabilities, but signed contrasts remain model-specific. Direct semantic-label output adds only small gains once category names are visible. A targeted 2 × 2 follow-up associates the Llama-3.1-70B Chinese-input residual primarily with procedural-block language on average, moderated by relation-definition language; alternate-label and crossed-label checks further show that exact label wording and language can shrink or reverse the signed contrast. We use semantic label anchoring only as descriptive shorthand. The result is a scoped measurementvalidity finding for Chinese-English XNLI and the tested prompt family, not a claim of invariance across language pairs or prompt paraphrases.
%U https://aclanthology.org/2026.oracle-main.35/
%P 515-533

Markdown (Informal)

[Prompt as Stratified Interface: Decomposing Label-Mediated Effects in Chinese-English NLI](https://aclanthology.org/2026.oracle-main.35/) (Zhao et al., ORACLE 2026)

• Prompt as Stratified Interface: Decomposing Label-Mediated Effects in Chinese-English NLI (Zhao et al., ORACLE 2026)

ACL

• Hua Zhao, Zhiqing Yang, and Michelle Mingyue Gu. 2026. Prompt as Stratified Interface: Decomposing Label-Mediated Effects in Chinese-English NLI. In The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE), pages 515–533, Budapest, Hungary. Association for Computational Linguistics.