Pramit Bhattacharyya — accepted AI-conference papers

2025

A Case Study of Cross-Lingual Zero-Shot Generalization for Classical Languages in LLMs

V.S.D.S.Mahesh Akavarapu, Hrishikesh Terdalkar, Pramit Bhattacharyya, Shubhangi Agarwal, Dr. Vishakha Deulgaonkar, Chaitali Dangarikar +2

ACL 2025finding

Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across diverse tasks and languages. In this study, we focus on natural language understanding in three classical languages—Sanskrit, Ancient Greek and Latin—to investigate the factors affecting cross-lingual zero-s…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

BanglaByT5: Byte-Level Modelling for Bangla

Pramit Bhattacharyya, Arnab Bhattacharya

EMNLP 2025

Large language models (LLMs) have achievedremarkable success across various natural lan-guage processing tasks. However, most LLMmodels use traditional tokenizers like BPE andSentencePiece, which fail to capture the finernuances of a morphologically rich languagelike Bangla (Bengali). In this work,

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Leveraging LLMs for Bangla Grammar Error Correction: Error Categorization, Synthetic Data, and Model Evaluation

Pramit Bhattacharyya, Arnab Bhattacharya

ACL 2025finding

Large Language Models (LLMs) perform exceedingly well in Natural Language Understanding (NLU) tasks for many languages including English. However, despite being the fifth most-spoken language globally, Grammatical Error Correction (GEC) in Bangla remains underdeveloped. In this work, we investigate…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗