arXiv AI
Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 23
Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach
arXiv:2603. 06660v2 Announce Type: replace-cross Abstract: Approximate Nearest Neighbor Search (ANNS) is fundamental to modern AI applications.
arXiv Machine Learning
Jun 9
GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
arXiv:2603. 24925v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems that rely on semantic search often fail to retrieve the complete set of evidence for complex queries, particularly when information is distributed across multiple sources.
arXiv AI
Aug 12
GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs
arXiv:2601. 18579v2 Announce Type: replace-cross Abstract: Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes.
arXiv AI
Jun 18
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
arXiv:2606. 18379v1 Announce Type: cross Abstract: Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet existing work addresses each in isolation.
arXiv Computation and Language
Aug 27
E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
E2Rank (Efficient Embedding-based Ranking) is a unified framework that extends a single text embedding model to perform both retrieval and listwise reranking. By treating the listwise prompt—constructed from the query and its top‑K candidates—as a pseudo‑relevance feedback query, E2Rank reranks via cosine similarity against precomputed document embeddings, avoiding costly autoregressive decoding. The approach achieves state‑of‑the‑art results on BEIR, competitive performance on the reasoning‑intensive BRIGHT benchmark, lower latency than existing LLM‑based rerankers, and improved embedding performance on MTEB—all within a single model.
arXiv AI
Aug 25
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval
arXiv:2608.22980v1 Announce Type: cross Abstract: Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embeddin...