Presents MedSci Skills, an open-source toolkit with deterministic integrity gates for verifying LLM-assisted clinical manuscripts against reporting guidelines like STARD, PRISMA, and STROBE.
Scientific Reports 13 (1): 14045
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Empirical test of Ai2 Asta finds high citation use in reports but significant instability in cited references and lack of concordance with retrieved documents across repeated identical queries.
GIScholarBench shows LLMs exhibit consistent overconfidence across three scholarly tasks in GIS, with different manifestations in factual retrieval, citation expansion, and idea generation.
LLM chat systems show large differences in reference quantity and quality, but users rarely click or engage with them.
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.
citing papers explorer
-
Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Auditable Biomedical Informatics Architecture
Presents MedSci Skills, an open-source toolkit with deterministic integrity gates for verifying LLM-assisted clinical manuscripts against reporting guidelines like STARD, PRISMA, and STROBE.
-
Unraveling the Ai2 Asta Scholarly Research Assistant Citation System
Empirical test of Ai2 Asta finds high citation use in reports but significant instability in cited references and lack of concordance with retrieved documents across repeated identical queries.
-
GIScholarBench: Benchmarking LLM Overconfidence in GIS Research
GIScholarBench shows LLMs exhibit consistent overconfidence across three scholarly tasks in GIS, with different manifestations in factual retrieval, citation expansion, and idea generation.
-
Analyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems
LLM chat systems show large differences in reference quantity and quality, but users rarely click or engage with them.
-
The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.