An accurate differential diagnosis (DDx) is a cornerstone of medical care, often reached through an iterative process of interpretation that combines clinical history, physical …
Querying, conversing, and controlling search and information-seeking interfaces using natural language are fast becoming ubiquitous with the rise and adoption of large-language …
Performing automatic reformulations of a user's query is a popular paradigm used in information retrieval (IR) for improving effectiveness--as exemplified by the pseudo …
Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance …
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents. Combining large language models (LLMs) with …
Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics …
Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion …
E Zhang, X Wang, P Gong, Y Lin, J Mao - arXiv preprint arXiv:2403.09142, 2024 - arxiv.org
Due to the advantages in the cost-efficiency and reproducibility, user simulation has become a promising solution to the user-centric evaluation of information retrieval systems …
In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly …