Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools
Not on the map. Why?
Abstract (arXiv)
Discussions around large language model (LLM) errors in clinical artificial intelligence (AI) generally center around precision errors like hallucinations. This perspective, targeting both clinicians and AI researchers, seeks to shift that discussion to recall errors, particularly in retrieval of patient-level data needed for many clinical AI tools. The perspective outlines types of errors and mitigation strategies, describes research directions in LLMs and retrieval, and provides an overview of retrieval evaluation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 29 Jun 2026.
Builds on
10 of 29 references.
References · 10
- 2017Attention Is All You Needcited by 59,932
- 2023A Survey of Large Language Modelscited by 2,537
- 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
- 2024Don't Use LLMs to Make Relevance Judgmentscited by 26
- 2025The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Modelscited by 24
- 2024On the Evaluation of Machine-Generated Reportscited by 23
- 2021Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVIDcited by 19
- 2021Refocusing on Relevance: Personalization in NLGcited by 18
- 2025LLM-Evaluation Tropes: Perspectives on the Validity of LLM-Evaluationscited by 14
- 2025Auto-ARGUE: LLM-Based Report Generation Evaluationcited by 14
Built on by
Not cited yet.