InstructRAG: Instructing Retrieval-Augmented Generation with Explicit Denoising

arXiv:2406.13629v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the retrieved contents, posing a significant challenge to the generation quality. Existing RAG methods typically address this challenge by directly predicting final answers despite potentially noisy inputs, resulting in an implicit denoising process that is difficult to interpret and verify. On the other hand, …

abstract accuracy arxiv challenge contents cs.cl cs.lg denoising however information language language models lms potential quality rag retrieval retrieval-augmented type