Research map / Large language models / Language, safety and interpretability
Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
Michael S Yao, Osbert Bastani, Alma Andersson, Tommaso Biancalani, Aicha BenTaieb, Claudia Iriondo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use LEON instead of best traditional optimizer BO-qEI | LLM optimizer (gpt-4o-mini) · Breast, TTNTD | TTNTD (months): 67.05 -> 72.43 | Improved |
| use LEON instead of Simulated Annealing | LLM optimizer · Lung, TTNTD | TTNTD (months): 29.29 -> 32.71 | Improved |
| use LEON instead of OPRO (LLM-based optimizer) | LLM optimizer · Breast, TTNTD | TTNTD (months): 55.68 -> 72.43 | Improved |
| use LEON instead of Majority baseline | LLM optimizer · ADR, NLL loss | NLL loss: 1.41 -> 12.4 | Hurt |
| use LEON instead of LLAMBO | LLM optimizer · Warfarin, RMSE | RMSE loss: 3.28 -> 1.36 | Improved |
| use LEON instead of human-prescribed treatments | LLM optimizer · Warfarin, RMSE | RMSE loss: 2.68 -> 1.36 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Eureka — Eureka: Human-Level Reward Design via Coding Large Language Models (ICLR 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DearLLM: Enhancing Personalized Healthcare via Large Language Models-Deduced Feature Correlations (AAAI 2025 · similarity 0.87)
- AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling (ICML 2025 · similarity 0.86)
- LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding (NeurIPS 2025 · similarity 0.86)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.85)
- MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making (NeurIPS 2024 · similarity 0.85)
- Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
