8 papers
Reproducing Adaptive Reranking for Reasoning-Intensive IR
Mandeep Rathee, V Venktesh, Sean MacAvaney +1
The classical cascading pipeline of retrieve--rerank suffers from a bounded recall problem, stemming from limitations of the first-stage retriever. Most current approaches address…
Think Right, Not More: Test-Time Scaling for Numerical Claim Verification
Primakov Chungkham, V Venktesh, Vinay Setty +1
Fact-checking real-world claims, particularly numerical claims, is inherently complex that require multistep reasoning and numerical reasoning for verifying diverse aspects of the…
Test-time Corpus Feedback: From Retrieval to RAG
Mandeep Rathee, V Venktesh, Sean MacAvaney +1
Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from exte…
Evaluating List Construction and Temporal Understanding capabilities of Large Language Models
Alexandru Dumitru, V Venktesh, Adam Jatowt +1
Large Language Models (LLMs) have demonstrated immense advances in a wide range of natural language tasks. However, these models are susceptible to hallucinations and errors on par…
ir_explain: a Python Library of Explainable IR Methods
Sourav Saha, Harsh Agarwal, V Venktesh +4
While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the us…
Breaking the Lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets
Mandeep Rathee, V Venktesh, Sean MacAvaney +1
Advanced relevance models, such as those that use large language models (LLMs), provide highly accurate relevance estimations. However, their computational costs make them infeasib…