AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Evidential Reasoning Advances Interpretable Real-World Disease Screening

Chenyu Lian, Hong-Yu Zhou, Jing Qin

ICML 2026 · Large language models › Retrieval and knowledge · approach: Domain-specific QA datasets · 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
add evidence-aware reasoning on top of evidence retrieval (ablation)EviScreen · JSIECSpe@95%R: 91.48 -> 94.74Improved
add evidence retrieval on top of evidence-aware reasoning (ablation)EviScreen · RIADDSpe@95%R: 61.86 -> 72.92Improved
add evidence-aware reasoning to retrieval only (ablation)EviScreen · RIADDAUROC: 90.42 -> 91.32Improved
remove evidence retrieval (reasoning only) vs retrieval only (ablation)EviScreen · RIADDAUROC: 90.42 -> 86.12Hurt
use dual knowledge banks with contrastive retrieval instead of normal-only PatchCore (same foundation models)Training-free variant · JSIECAUROC: 94.96 -> 96.76Improved
replace fixed learned prototypes (CIPL) with scalable dual knowledge banksEviScreen · CheXpertSpe@95%R: 68.09 -> 84.04Improved
evidential reasoning vs direct fine-tuning of foundation model (FM)EviScreen · JSIECSpe@100%R: 78.39 -> 91.27Improved
evidential reasoning vs direct fine-tuning of foundation model (FM)EviScreen · CheXpertCSR: 57.41 -> 70.59Improved
increase number of samples in dual knowledge banks (ablation)Training-free variant · ophthalmology validationSpe@X%RImproved
use foundation-model features in PatchCore instead of ImageNet-pretrained (ablation)PatchCore · four test setsscreening metrics: 92.12 -> 94.96 AUROC (JSIEC)Improved

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