Hierarchical BM25: Lexical Search at Billion-Document Scale

2026-08-04T08:52:11Ze4ad8cdba98bd6679bb99d59ced2e2d5e9e173868a7561ca25d4e76e4b33aad0
BM25GraphRAGLLMMixture-of-ExpertsRAGads-retrievalcross-encodergenerative-recommendationinformation-retrievalquery-expansionrecommendation-systemsrerankingresearchsemantic-searchtext-video-retrieval

What happened

Collection of arXiv information-retrieval and recommendation research papers. Topics include billion-scale hierarchical BM25, semantic evidence for lexical query expansion, LLM-assisted cultural heritage, multimodal text-video retrieval, graph-grounded recommendation, robustness evaluation of GraphRAG and vector RAG, generative recommender optimization, reranker training, and real-time ads retrieval. The content is academic and does not describe a specific vulnerability, exploit, malware, or security incident.

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
arxiv_cs_ir
Record identifier
e4ad8cdba98bd6679bb99d59ced2e2d5e9e173868a7561ca25d4e76e4b33aad0
Enrichment time
2026-08-04T08:52:11Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

Record · Hierarchical BM25: Lexical Search at Billion-Document Scale · Baitaphish