Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy
This work addresses the need for better utility assessment in RAG systems to enhance question-answering performance, though it appears incremental as it builds on existing RAG components with a philosophical inspiration.
The paper tackles the problem of prioritizing high-utility results in Retrieval-Augmented Generation (RAG) systems by proposing an Iterative utiliTy judgmEnt fraMework (ITEM), which significantly improves utility judgments, ranking, and answer generation over baselines on datasets like TREC DL and NQ.
Relevance and utility are two frequently used measures to evaluate the effectiveness of an information retrieval (IR) system. Relevance emphasizes the aboutness of a result to a query, while utility refers to the result's usefulness or value to an information seeker. In Retrieval-Augmented Generation (RAG), high-utility results should be prioritized to feed to LLMs due to their limited input bandwidth. Re-examining RAG's three core components -- relevance ranking derived from retrieval models, utility judgments, and answer generation -- aligns with Schutz's philosophical system of relevances, which encompasses three types of relevance representing different levels of human cognition that enhance each other. These three RAG components also reflect three cognitive levels for LLMs in question-answering. Therefore, we propose an Iterative utiliTy judgmEnt fraMework (ITEM) to promote each step in RAG. We conducted extensive experiments on retrieval (TREC DL, WebAP), utility judgment task (GTI-NQ), and factoid question-answering (NQ) datasets. Experimental results demonstrate significant improvements of ITEM in utility judgments, ranking, and answer generation upon representative baselines.