Researchers have introduced ADORE, an iterative framework designed to enhance Large Language Model (LLM)-based query expansion for information retrieval. Unlike generation-driven methods that can lead to retrieval drift, ADORE uses retrieval outcomes as feedback for subsequent expansion rounds. This iterative process involves an LLM generating passages, a retriever assessing corpus response, and a relevance evaluator judging retrieved documents against the original query. ADORE has demonstrated significant performance improvements across multiple benchmarks, including TREC Deep Learning, BEIR, and BRIGHT, outperforming traditional methods like BM25 and prior query expansion techniques. AI
IMPACT This iterative approach to query expansion could lead to more accurate and relevant search results in LLM-powered information retrieval systems.
RANK_REASON The cluster contains an academic paper detailing a new framework for LLM-based query expansion.
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
