Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
Year: 2025
Type: conference-paper
Abstract: Retrieval Augmented Generation (RAG) has shown strong capability in enhancing language models' knowledge and reducing AI generative hallucinations, driving its widespread use. However, complex tasks requiring multi-round retrieval remain challenging, and early attempts tend to be overly optimistic without a good sense of self-skepticism. Current multi-round RAG systems may continue searching even when enough information has already been retrieved, or they may provide incorrect answers without having sufficient information or knowledge. Existing solutions either require large amounts of expensive human-labeled process supervision data or lead to subpar performance.
Authors: Diji Yang, Linda Zeng, Jinmeng Rao, Yi Zhang
Institution: University of California, Santa Cruz
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412376899