#neural-ir News & Analysis

3 articles tagged with #neural-ir. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · May 296/10

🧠

Xetrieval: Mechanistically Explaining Dense Retrieval

Researchers introduce Xetrieval, a mechanistic framework that explains how dense retrieval models assign relevance scores by decomposing high-dimensional embeddings into interpretable features. The method uses a lightweight reasoning internalizer to enrich embeddings with reasoning information and provides human-readable feature-level explanations of retrieval decisions, advancing transparency in neural information retrieval systems.

AINeutralarXiv – CS AI · May 296/10

🧠

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies

Researchers demonstrate that dense neural retrievers contain extractable sparse features matching BM25-ready vocabularies without specialized training. Sparse Autoencoders can decompose frozen dense retrievers into classical sparse retrieval components, achieving competitive or superior performance to single-vector methods while requiring no retrieval-specific supervision.

AIBullisharXiv – CS AI · Apr 146/10

🧠

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

Researchers introduce M³KG-RAG, a novel multimodal retrieval-augmented generation system that enhances large language models by integrating multi-hop knowledge graphs with audio-visual data. The approach improves reasoning depth and answer accuracy by filtering irrelevant information through a new grounding and pruning mechanism called GRASP.

$KG