Hallucinations Improve LLMs in Drug Discovery
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Claims that LLMs can achieve better performance in drug discovery tasks with text hallucinations compared to input prompts without hallucination. Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination. In addition, hallucinations generated by GPT-4o provide the most consistent improvements across models.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack