New LLM-IRA method improves retrieval ranking aggregation

Researchers have developed LLM-IRA, a novel method for aggregating rankings from multiple retrieval systems, particularly useful for RAG applications. This approach utilizes large language models for pairwise judgments on documents with high disagreement, learning fusion weights interactively. Experiments on the BEIR benchmark and TREC Deep Learning tracks demonstrated that LLM-IRA matches or surpasses strong static fusion baselines, achieving statistical significance on several benchmarks with minimal LLM calls. AI

IMPACT This method could enhance the performance of RAG systems by improving document reranking with fewer LLM calls.

RANK_REASON Academic paper detailing a new method for information retrieval. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• BEIR
• DBpedia
• Hugging Face
• Llama 3.1 8B-Instruct
• LLM-IRA
• NFCorpus
• TREC Deep Learning tracks

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →