Mandeep Rathee
2 papers · Latest:
Information Retrieval
When More Reformulations Hurt: Avoiding Drift using Ranker Feedback
ReformIR is a budget-aware retrieval framework that uses a teacher reranker to adaptively select query reformulations and documents, improving recall while avoiding drift.
2605.00560
Information RetrievalReproducing Adaptive Reranking for Reasoning-Intensive IR
This paper reproduces Graph-based Adaptive Reranking (GAR) for reasoning-intensive IR, showing it boosts effectiveness with minimal overhead.
2604.27577
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.