@inproceedings{das-2026-quantifying,
title = "Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models",
author = "Das, Roumak",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.10/",
pages = "110--113",
ISBN = "979-8-89176-377-7",
abstract = "Multilingual Large Language Models (LLMs) often demonstrate impressive zero-shot capabilities on low-resource languages. However, for languages that share a script and significant lexical overlap with a high-resource language (HRL), models may exhibit negative transfer. Focusing on Kamtapuri (Rajbanshi), a distinct low-resource language of North Bengal, we investigate the extent to which SOTA models (e.g., GPT-5.1, Gemini 2.5) preserve distinct dialectal features versus reverting to the dominant language{'}s norms. We introduce the Kamta-Shibboleth-100 (Benchmark available at: https://github.com/kamtapuri-research/Kamta-Shibboleth-100-BENCHMARK), a diagnostic benchmark derived from a curated 400k-token corpus. Our evaluation reveals a significant discrepancy: while models show high receptive understanding (up to 88{\%} translation accuracy), they exhibit a 0{\%} Syntactic Competence Rate in zero-shot generation of distinct Kamtapuri morphology, compared to 96{\%}+ accuracy on a Standard Bengali control set. Even with 5-shot prompting, syntactic accuracy improves only to 10{\%}, while the Substitution Erasure Rate (SER) reaches 71{\%}, systematically replacing Kamtapuri vocabulary with Bengali cognates. We characterize this behavior not as a lack of knowledge, but as a strong alignment bias toward high-resource standards."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-2026-quantifying">
<titleInfo>
<title>Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roumak</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Multilingual Large Language Models (LLMs) often demonstrate impressive zero-shot capabilities on low-resource languages. However, for languages that share a script and significant lexical overlap with a high-resource language (HRL), models may exhibit negative transfer. Focusing on Kamtapuri (Rajbanshi), a distinct low-resource language of North Bengal, we investigate the extent to which SOTA models (e.g., GPT-5.1, Gemini 2.5) preserve distinct dialectal features versus reverting to the dominant language’s norms. We introduce the Kamta-Shibboleth-100 (Benchmark available at: https://github.com/kamtapuri-research/Kamta-Shibboleth-100-BENCHMARK), a diagnostic benchmark derived from a curated 400k-token corpus. Our evaluation reveals a significant discrepancy: while models show high receptive understanding (up to 88% translation accuracy), they exhibit a 0% Syntactic Competence Rate in zero-shot generation of distinct Kamtapuri morphology, compared to 96%+ accuracy on a Standard Bengali control set. Even with 5-shot prompting, syntactic accuracy improves only to 10%, while the Substitution Erasure Rate (SER) reaches 71%, systematically replacing Kamtapuri vocabulary with Bengali cognates. We characterize this behavior not as a lack of knowledge, but as a strong alignment bias toward high-resource standards.</abstract>
<identifier type="citekey">das-2026-quantifying</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.10/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>110</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models
%A Das, Roumak
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F das-2026-quantifying
%X Multilingual Large Language Models (LLMs) often demonstrate impressive zero-shot capabilities on low-resource languages. However, for languages that share a script and significant lexical overlap with a high-resource language (HRL), models may exhibit negative transfer. Focusing on Kamtapuri (Rajbanshi), a distinct low-resource language of North Bengal, we investigate the extent to which SOTA models (e.g., GPT-5.1, Gemini 2.5) preserve distinct dialectal features versus reverting to the dominant language’s norms. We introduce the Kamta-Shibboleth-100 (Benchmark available at: https://github.com/kamtapuri-research/Kamta-Shibboleth-100-BENCHMARK), a diagnostic benchmark derived from a curated 400k-token corpus. Our evaluation reveals a significant discrepancy: while models show high receptive understanding (up to 88% translation accuracy), they exhibit a 0% Syntactic Competence Rate in zero-shot generation of distinct Kamtapuri morphology, compared to 96%+ accuracy on a Standard Bengali control set. Even with 5-shot prompting, syntactic accuracy improves only to 10%, while the Substitution Erasure Rate (SER) reaches 71%, systematically replacing Kamtapuri vocabulary with Bengali cognates. We characterize this behavior not as a lack of knowledge, but as a strong alignment bias toward high-resource standards.
%U https://aclanthology.org/2026.loreslm-1.10/
%P 110-113
Markdown (Informal)
[Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models](https://aclanthology.org/2026.loreslm-1.10/) (Das, LoResLM 2026)
ACL