New KAMR retriever improves multi-hop retrieval for LLM question answering

Researchers have introduced KAMR, a novel knowledge-aligned multi-hop retriever designed to improve the accuracy of question answering systems that rely on composing multiple knowledge graph triplets. Unlike existing methods that rank triplets independently, KAMR distinguishes between strongly query-constrained anchor triplets and weakly aligned but structurally linked connected triplets. To address a lack of supervision for query-triplet alignment, a partial alignment dataset was created by masking triplet elements and prompting an LLM to generate corresponding queries. KAMR consistently enhances multi-hop retrieval and downstream question answering performance across various benchmarks and LLM backbones. AI

IMPACT Enhances LLM reasoning capabilities by improving how they access and synthesize information from knowledge graphs.

RANK_REASON The item is a research 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) →

• alphaXiv
• arXiv
• Bibliographic Explorer
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• model release

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