AI Paper Atlas

Research map / Large language models / Agents, code and math

Can Large Language Models Match the Conclusions of Systematic Reviews?

Christopher Polzak, Alejandro Lozano, Min Woo Sun, James Burgess, Yuhui Zhang, Kevin Wu, Chia-Chun Chiang, Jeffrey J Nirschl, Serena Yeung-Levy

ICLR 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 13 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 reasoning model DeepSeek R1 instead of non-reasoning DeepSeek V3DeepSeek 671B · MedEvidenceaccuracyHurt
distill reasoning (R1) into Llama 3.3 70BLlama 3.3 70B · MedEvidenceaccuracyImproved
add medical fine-tuning to base LLMsmedical-finetuned models vs base · MedEvidenceaccuracyHurt
increase model size from 7B to 70BLLM families · MedEvidenceaccuracyImproved
increase model size beyond 70BLLM families · MedEvidenceaccuracyNo clear effect
use expert-guided prompt instead of basic prompt (ablation)DeepSeek V3 · MedEvidenceaccuracy: nearly 20% dropHurt
use expert-guided prompt instead of basic prompt (ablation)five worst models under basic prompt · MedEvidenceaccuracyImproved
provide full text instead of abstract only (ablation)DeepSeek R1 · MedEvidenceaccuracy: +4.8%Improved
provide abstracts only instead of full text (ablation)HuatuoGPT-o1-70B · MedEvidenceaccuracy: +24.8%Improved
increase source concordance from 0% to 100%DeepSeek V3 · MedEvidenceaccuracy: 41.21 -> 92.45Improved
increase number of relevant sourcesLLMs · MedEvidenceaccuracyNo clear effect
increase input token lengthLLMs · MedEvidenceaccuracyHurt

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