Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Open Access

Evaluating Medium Scale, Open-Source Large Language Models: Towards Decision Support in a Precision Oncology Care Delivery Context

View Full Paper
Ask AI
Bookmark
Share

Authors

KKKevin KaufmesGMGeorg MathesDVDilyana Vladimirova

Discussion

Loading...

Member takes

Overview

Observational analysis assesses response quality from large language models in precision oncology, indicating reliability issues.

Key Points

  • Response quality from medium-scale large language models in precision oncology remains modest, with notable reliability issues.
  • Only 5 of 60 domain experts completed the survey fully, revealing issues like outdated information and factual errors in responses.
  • Three large language models were assessed for their capability to support molecular tumor boards based on expert-crafted questions.
  • Improvements such as retrieval-augmented-generation are essential for enhancing information accuracy and patient safety.

Cite This Study

Kaufmes et al. (2025) studied this question.

synapsesocial.com/papers/68c23b4ab210217d64783db8https://doi.org/10.3233/shti251382
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Large language model integrations in cancer decision-making: a systematic review and meta-analysis2025 · 50 citations
  2. 2Large Language Models for Cancer Communication: Evaluating Linguistic Quality, Safety, and Accessibility in Generative AI (Preprint)2025
  3. 3Evaluating the Efficacy of Large Language Models in Addressing Patient-Centric Inquiries in Multiple Cancers2025
  4. 4Personalizing communication with the patient: large language models2025 · 2 citations
  5. 5Large Language Models in Lung Cancer: Systematic Review.2025 · 8 citations