@inproceedings{rahman-etal-2026-calques,
title = "Why Calques Look Rare in {H}indi Model Output: A Human-Anchored Measurement Study",
author = "Rahman, Abdur and
Sharma, Vasu and
Saifullah, Mohammad",
editor = "Ranaldi, Leonardo and
Pucci, Giulia and
Ranaldi, Federico and
Valentino, Marco and
Birch, Alexandra and
Zanzotto, Fabio Massimo",
booktitle = "The Proceedings of the Workshop on Open Reasoning Across Cultures Languages ({ORACLE})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.oracle-main.21/",
pages = "316--328",
ISBN = "979-8-89176-483-5",
abstract = "Large language models write Hindi that carries the shape of English, and measuring how often is the open problem, because the phraselevel instruments available are lexical and brittle. We build a 26-pair Hindi contrast set over eight idiom families, verified by three native Hindi speakers. Prompt framing moves supplied-candidate scores toward the calque: an English-literal cue shifts them in 8 of 8 families, and a separate translate-from-English instruction shifts them again, with the direction holding on a family split frozen before the outcome was seen. Free generation appears to show far less calquing, so we audit the lexical indicator behind that appearance against native-speaker judgement. Its precision on its own positives is 1.00, while 24 of 60 sampled negatives are calques by majority verdict, and the misses concentrate in the families where its exact-match trigger was never observed to fire. The apparent scarcity is substantially a property of the instrument. We recommend that detectors of this form report coverage alongside hits."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2026-calques">
<titleInfo>
<title>Why Calques Look Rare in Hindi Model Output: A Human-Anchored Measurement Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasu</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Saifullah</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>Large language models write Hindi that carries the shape of English, and measuring how often is the open problem, because the phraselevel instruments available are lexical and brittle. We build a 26-pair Hindi contrast set over eight idiom families, verified by three native Hindi speakers. Prompt framing moves supplied-candidate scores toward the calque: an English-literal cue shifts them in 8 of 8 families, and a separate translate-from-English instruction shifts them again, with the direction holding on a family split frozen before the outcome was seen. Free generation appears to show far less calquing, so we audit the lexical indicator behind that appearance against native-speaker judgement. Its precision on its own positives is 1.00, while 24 of 60 sampled negatives are calques by majority verdict, and the misses concentrate in the families where its exact-match trigger was never observed to fire. The apparent scarcity is substantially a property of the instrument. We recommend that detectors of this form report coverage alongside hits.</abstract>
<identifier type="citekey">rahman-etal-2026-calques</identifier>
<location>
<url>https://aclanthology.org/2026.oracle-main.21/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>316</start>
<end>328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Why Calques Look Rare in Hindi Model Output: A Human-Anchored Measurement Study
%A Rahman, Abdur
%A Sharma, Vasu
%A Saifullah, Mohammad
%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 rahman-etal-2026-calques
%X Large language models write Hindi that carries the shape of English, and measuring how often is the open problem, because the phraselevel instruments available are lexical and brittle. We build a 26-pair Hindi contrast set over eight idiom families, verified by three native Hindi speakers. Prompt framing moves supplied-candidate scores toward the calque: an English-literal cue shifts them in 8 of 8 families, and a separate translate-from-English instruction shifts them again, with the direction holding on a family split frozen before the outcome was seen. Free generation appears to show far less calquing, so we audit the lexical indicator behind that appearance against native-speaker judgement. Its precision on its own positives is 1.00, while 24 of 60 sampled negatives are calques by majority verdict, and the misses concentrate in the families where its exact-match trigger was never observed to fire. The apparent scarcity is substantially a property of the instrument. We recommend that detectors of this form report coverage alongside hits.
%U https://aclanthology.org/2026.oracle-main.21/
%P 316-328
Markdown (Informal)
[Why Calques Look Rare in Hindi Model Output: A Human-Anchored Measurement Study](https://aclanthology.org/2026.oracle-main.21/) (Rahman et al., ORACLE 2026)
ACL