Jia-Huei Ju

Recent work has suggested that adding irrelevant documents to the input of retrieval-augmented generation (RAG) systems can improve question-answering performance, a phenomenon referred to as the '' Power of Noise. '' This motivated investigations into the role of noise in information retrieval....

Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (i.e., facts), which can thereby be synthesized into a comprehensive output. In this work, we propose CoveR, a dense r...

Advancements in retrieval models necessitate re-indexing, a computationally expensive process for large-scale production environments. While updating only the query encoder and continuing to use the old index could be a promising middle ground, dense retrieval systems suffer severe performance dr...