Yash Bhaskar supervised by Dr. Parameswari Krishnamurthy received his Master of Science – Dual Degree in Computational Linguistics (CLD) by Research. Here’s a summary of his research work on Improving Machine Translation with Large Language Models

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their application to Machine Translation (MT), particularly for low-resource languages, remains an active area of research. This thesis investigates the adaptation of LLMs for machine translation involving English and Indian languages, addressing challenges in assessment, fine-tuning, alignment, evaluation, and inference efficiency. We begin by assessing the translation capabilities of popular LLMs (LLaMA, Mistral, Bloom) for 22 Indian languages under zero-shot and in-context learning settings. Our findings reveal that while raw LLMs exhibit limited translation quality, parameter-efficient fine-tuning using LoRA significantly improves performance, with two-stage fine-tuning achieving results competitive with specialized MT systems. Building on these insights, we investigate fine-tuning strategies for extremely low-resource Indic languages through participation in the WMT 2024 shared task. Our experiments across Assamese, Mizo, Khasi, and Manipuri demonstrate that fine-tuned LLMs substantially outperform models trained from scratch, and that multilingual approaches consistently surpass monolingual ones. We then explore data-efficient alignment strategies using preference optimization. Our Progressive Perturbation approach with Kahneman-Tversky Optimization (KTO) demonstrates that targeted perturbations of training data can enhance translation quality without requiring extensive parallel corpora. To address the challenge of evaluating MT for low-resource languages, we conduct a comprehensive analysis of statistical and neural evaluation metrics, examining their stability, consistency, and correlation with human judgments. Finally, we tackle inference efficiency through DistillBeam, a multi-trajectory knowledge distillation framework for speculative decoding. By aggregating supervision from multiple high-probability teacher trajectories, DistillBeam achieves wall-clock speedups of 35-65% over autoregressive decoding across 20 languages. This thesis contributes practical methodologies and empirical insights for deploying LLM-based translation systems for Indian languages, balancing translation quality with computational efficiency. 

July 2026