作者位次 #2/4SIGIR 2026Oral· Information Retrieval (Reproducibility)
Can QPP Choose the Right Query variant? Evaluating Query Variant Selection for RAG Pipelines
Negar Arabzadeh · Andrew Drozdov · Michael Bendersky · Matei Zaharia
摘要
Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines, enabling the generation of multiple semantically equivalent query variants. However, executing the full pipeline for every reformulation is computationally...