AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

REACT-LLM: A Benchmark for Evaluating LLM Integration with Causal Features in Clinical Prognostic Tasks

Linna Wang, Zhixuan You, Qihui Zhang, Jiunan Wen, Ji Shi, Yimin Chen, Yusen Wang, Fanqi Ding, Ziliang Feng, Li Lu

AAAI 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 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 LLMs instead of traditional ML modelsLLM direct prompting · 7 clinical outcomes, MIMIC-III/IVAUROC/AUPRC: LLMs lag ML baselines by about 10-20%Hurt
use Gemini-2-Flash instead of best ML model on EarlyICUGemini-2-Flash · MIMIC-III EarlyICUAUPRC: 0.8473 -> 0.8540Improved
add in-context learning prompting (ablation)LLMs · 7 clinical outcomesAUROC/AUPRC/F1: surpasses baseline 41 times, best in 22Improved
add self-reflection prompting (ablation)LLMs · 7 clinical outcomesAUROC/AUPRC/F1: exceeds baseline in 38 cases, leads in 19Improved
add ICL to Gemini-2-Pro on Readmit30 (ablation)Gemini-2-Pro · Readmit30AUROC: +0.077Improved
add CoT to DeepSeek-R1 (ablation)DeepSeek-R1 · Readmit30AUROC: +0.0912 AUROC, +0.0271 AUPRCImproved
add any prompting strategy (ablation)LLMs · 7 clinical outcomesAUROCNo clear effect
use JSON instead of RCF input format (ablation)Qwen3-235b · MIMIC-IIIAUROC/AUPRC/F1: up to +0.064Improved
use narrative serialization instead of RCF input format (ablation)Gemini-2-Flash · MIMIC-IIIAUROC/AUPRC: +0.051 AUROC, +0.026 AUPRCImproved
use RCF format instead of NS or TBNL (ablation)GPT-o3-mini · MIMIC-IIIAUROC/AUPRC/F1Improved
restrict input to causal-discovery features (DirectLiNGAM) (ablation)LLMs · MIMIC-III and MIMIC-IVAUROCHurt
restrict input to GES causal features (ablation)DeepSeek-R1, Qwen3-8b, Qwen3-235b · MIMIC-III and MIMIC-IVAUROCImproved

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