Get Started
Home
Topics
Search
Library
Research questionCan prompt phrasing reliably improve LLM-derived chemical features for drug-toxicity prediction?Minor changes in prompt phrasing can alter LLM outputs, making it unclear whether prompt optimization produces stable chemical features for toxicity models. This variability complicates the use of LLM-generated features in a costly drug-development process.
AI
Evaluation & Benchmarks
Health
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Analysis of Prompt Engineering for Drug Toxicity PredictionThe study evaluates LLM prompts that vary job role, structure, and rule interpretation, then passes the resulting feature values to machine-learning algorithms. It reports that natural LLM variance outweighed prompt fine-tuning, while chemoinformatic code extraction produced substantial performance improvements. The source does not specify a particular LLM, dataset, toxicity endpoint, or access setup.research paper · Sep 3, 2026
Related questions
How can prompt representations distinguish specificity to expose fine-grained LLM weaknesses?How should LLM safety be evaluated when harmful prompts vary in implicitness and sophistication?How can LLMs avoid unsafe pharmacological inferences driven by drug-name affixes?How can LLM prompts be automatically refined from recurring reasoning errors without laborious manual engineering?