Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models

Roumak Das


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.
Anthology ID:
2026.loreslm-1.10
Volume:
Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Hansi Hettiarachchi, Tharindu Ranasinghe, Alistair Plum, Paul Rayson, Ruslan Mitkov, Mohamed Gaber, Damith Premasiri, Fiona Anting Tan, Lasitha Uyangodage
Venue:
LoResLM
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
110–113
Language:
URL:
https://aclanthology.org/2026.loreslm-1.10/
DOI:
Bibkey:
Cite (ACL):
Roumak Das. 2026. Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models. In Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026), pages 110–113, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Quantifying Cross-Lingual Interference: Algorithmic Standardization of Kamtapuri in Large Language Models (Das, LoResLM 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.loreslm-1.10.pdf