3 papers
cs.CL2025
From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation
Amit Barman, Atanu Mandal, Sudip Kumar Naskar
In multilingual nations like India, access to legal information is often hindered by language barriers, as much of the legal and judicial documentation remains in English. Legal Ma…
cs.IR2025
HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
Payel Santra, Madhusudan Ghosh, Debasis Ganguly +2
Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). Howe…
cs.LG2025
Unified Graph Networks (UGN): A Deep Neural Framework for Solving Graph Problems
Rudrajit Dawn, Madhusudan Ghosh, Partha Basuchowdhuri +1
Deep neural networks have enabled researchers to create powerful generalized frameworks, such as transformers, that can be used to solve well-studied problems in various applicatio…