AI RESEARCH
A Systematic Study of Pseudo-Relevance Feedback with LLMs
arXiv CS.CL
•
ArXi:2603.11008v1 Announce Type: cross Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the given feedback text is used to refine the query representation. However, the independent role that each dimension plays is unclear, as both are often entangled in empirical evaluations.