Feb. 22, 2024, 5:42 a.m. | Lo\"ic Rakotoson, Sylvain Massip, Fr\'ejus A. A. Laleye

cs.LG updates on arXiv.org arxiv.org

arXiv:2402.13897v1 Announce Type: cross
Abstract: Information retrieval is a rapidly evolving field. However it still faces significant limitations in the scientific and industrial vast amounts of information, such as semantic divergence and vocabulary gaps in sparse retrieval, low precision and lack of interpretability in semantic search, or hallucination and outdated information in generative models. In this paper, we introduce a two-block approach to tackle these hurdles for long documents. The first block enhances language understanding in sparse retrieval by query …

abstract arxiv cs.ai cs.cl cs.ir cs.lg divergence hallucination industrial information interpretability limitations low paradigm precision reasoning retrieval science search semantic transparency type vast

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Codec Avatars Research Engineer

@ Meta | Pittsburgh, PA