Showing cs.IRShow all
3 papers · 1 filter
cs.IR2026
: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives
Aarush Sinha, Rahul Seetharaman, Aman Bansal
Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose ECIsem, a validity-weighted diagnostic that ranks…
cs.IR2026
Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
Aarush Sinha
Training effective dense retrieval models typically relies on hard negative (HN) examples mined from large document corpora using methods such as BM25 or cross-encoders, which requ…
cs.IR2025
BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives
Aarush Sinha, Pavan Kumar S, Roshan Balaji +1
Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models bas…