CRAWLDoc: A System for Contextual Ranking and Bibliographic Metadata Extraction from Web Resources | Information Retrieval Research

Published at #IRRJ: "CRAWLDoc: A System for Contextual Ranking and Bibliographic Metadata Extraction from Web Resources" by Fabian Karl and Ansgar Scherp. #DocumentRanking, #BibliographicMetadataExtraction, #ScholarlyDataset

https://doi.org/10.54195/irrj.23861

LLMs excel at document ranking, enabling efficient N-day vulnerability detection in patch diffs
noperator.dev/posts/document-ranking-f...
#llmtechnology #securityresearch #patchanalysis #vulnerabilitydetection #documentranking