Showing cs.IRShow all
3 papers · 1 filter
cs.IR2026
Scaling Laws for Cross-Encoder Reranking
Rahul Seetharaman, Aman Bansal, Hamed Zamani +1
Scaling laws are well studied for language models and first-stage retrieval, but not for reranking. We present the first systematic study of scaling laws for cross-encoder reranker…
cs.IR2026
What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals
Aarush Sinha, Rahul Seetharaman, Aman Bansal
Which properties of hard-negative supervision track dense-retriever transfer before training? We compare lexical noncoverage, frozenencoder similarity statistics, hardness proxies,…
cs.IR2025
InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
Rahul Seetharaman, Kaustubh D. Dhole, Aman Bansal
Large Language Models (LLMs) have demonstrated significant strides across various information retrieval tasks, particularly as rerankers, owing to their strong generalization and k…