3 papers
cs.IR2026
Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
Nilanjan Sinhababu, Soumedhik Bharati, Debasis Ganguly +1
Large Language Models (LLM) have been widely used in reranking. Computational overhead and large context lengths remain a challenging issue for LLM rerankers. Efficient reranking u…
cs.IR2025
Modeling Ranking Properties with In-Context Learning
Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly +1
While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives…
cs.IR2024
Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model
Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly +2
A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning.…