AI Paper Atlas

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

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use LEON instead of best traditional optimizer BO-qEILLM optimizer (gpt-4o-mini) · Breast, TTNTDTTNTD (months): 67.05 -> 72.43Improved
use LEON instead of Simulated AnnealingLLM optimizer · Lung, TTNTDTTNTD (months): 29.29 -> 32.71Improved
use LEON instead of OPRO (LLM-based optimizer)LLM optimizer · Breast, TTNTDTTNTD (months): 55.68 -> 72.43Improved
use LEON instead of Majority baselineLLM optimizer · ADR, NLL lossNLL loss: 1.41 -> 12.4Hurt
use LEON instead of LLAMBOLLM optimizer · Warfarin, RMSERMSE loss: 3.28 -> 1.36Improved
use LEON instead of human-prescribed treatmentsLLM optimizer · Warfarin, RMSERMSE loss: 2.68 -> 1.36Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy