collaborators

6 papers

cs.IR2026

Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG

Utshab Kumar Ghosh, Debayan Mukhopadhyay, Shubham Chatterjee

Retrieval evaluation for retrieval-augmented generation (RAG) is increasingly designed around whether retrieved passages contain evidence that can support generation, rather than t…

cs.IR2026

When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design

Utshab Kumar Ghosh, Shubham Chatterjee

Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We study when this actually helps…

cs.IR2026

Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search

Debayan Mukhopadhyay, Utshab Kumar Ghosh, Shubham Chatterjee

Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the documen…

cs.IR2026

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking

Utshab Kumar Ghosh, Shubham Chatterjee

Entity-aware document retrieval uses query-associated entities as ranking signals, assuming that semantically relevant entities are also useful retrieval signals. We show this assu…

cs.IR2026

Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions

Utshab Kumar Ghosh, Ashish David, Shubham Chatterjee

Reproducibility must validate architectural robustness, not just numerical accuracy. We evaluate ColBERT-v2 and ConstBERT across five dimensions, finding that while ConstBERT repro…

cs.IR2026

Single-Turn LLM Reformulation Powered Multi-Stage Hybrid Re-Ranking for Tip-of-the-Tongue Known-Item Retrieval

Debayan Mukhopadhyay, Utshab Kumar Ghosh, Shubham Chatterjee

Retrieving known items from vague descriptions, Tip-of-the-Tongue (ToT) retrieval, remains a significant challenge. We propose using a single call to a generic 8B-parameter LLM for…