LitSense 2.0: AI-powered biomedical information retrieval with sentence and passage level knowledge discovery
- 16 May 2025
- journal article
- Published by Oxford University Press (OUP) in Nucleic Acids Research
- Vol. 53 (W1) , W361-W368
Abstract
LitSense 2.0 (https://www.ncbi.nlm.nih.gov/research/litsense2/) is an advanced biomedical search system enhanced with dense vector semantic retrieval, designed for accessing literature on sentence and paragraph levels. It provides unified access to 38 million PubMed abstracts and 6.6 million full-length articles in the PubMed Central (PMC) Open Access subset, encompassing 1.4 billion sentences and ∼300 million paragraphs, and is updated weekly. Compared to PubMed and PMC, the primary platforms for biomedical information search, LitSense offers cross-platform functionality by searching seamlessly across both PubMed and PMC and returning relevant results at a more granular level. Building on the success of the original LitSense launched in 2018, LitSense 2.0 introduces two major enhancements. The first is the addition of paragraph-level search: users can now choose to search either against sentences or against paragraphs. The second is improved retrieval accuracy via a state-of-the-art biomedical text encoder, ensuring more reliable identification of relevant results across the entire biomedical literature.Keywords
Funding Information
- National Institutes of Health
This publication has 33 references indexed in Scilit:
- FoodAtlas: Automated knowledge extraction of food and chemicals from literatureComputers in Biology and Medicine, 2024
- PubMed and beyond: biomedical literature search in the age of artificial intelligenceEBioMedicine, 2024
- BactInt: A domain driven transfer learning approach for extracting inter-bacterial associations from biomedical textComputational Biology and Chemistry, 2024
- MedCPT: Contrastive Pre-trained Transformers with large-scale PubMed search logs for zero-shot biomedical information retrievalBioinformatics, 2023
- Learned Dense Representations for Ranking2022
- Complement Lexical Retrieval Model with Semantic Residual Embeddings2021
- Cardiovascular informatics: building a bridge to data harmonyCardiovascular Research, 2021
- MedSTS: a resource for clinical semantic textual similarityLanguage Resources and Evaluation, 2018
- How user intelligence is improving PubMedNature Biotechnology, 2018
- BIOSSES: a semantic sentence similarity estimation system for the biomedical domainBioinformatics, 2017