2 papers
cs.CL2025
The Art of Breaking Words: Rethinking Multilingual Tokenizer Design
Aamod Thakur, Ajay Nagpal, Atharva Savarkar +7
While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Mode…
cs.CL2025
Intent Aware Context Retrieval for Multi-Turn Agricultural Question Answering
Abhay Vijayvargia, Ajay Nagpal, Kundeshwar Pundalik +5
Indian farmers often lack timely, accessible, and language-friendly agricultural advice, especially in rural areas with low literacy. To address this gap in accessibility, this pap…