AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

CRAF: A Clinical Reasoning-Adaptive Framework via Reinforcement Learning for Similar Case Retrieval

Jie Lin, Lei Jiang, Zongyi Chen, Liansheng Wang

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Efficient and adaptive thinking · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes CRAF, a reinforcement-learning framework that adapts clinical reasoning for similar case retrieval, with explicit chain-of-thought to surface implicit reasoning cues in clinical data.

Problem

Similar clinical case retrieval is hard because implicit reasoning cues in clinical data prevent current retrieval models from capturing deep semantic relations.

Approach

Applies reinforcement learning to reasoning-based retrieval so that explicit chain-of-thought generation is adapted to clinical case retrieval; details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CRAF-8B query rewritingQwen3-Embedding retriever · PMC-PatientsAVG: 36.33 -> 39.87Improved
add CRAF-8B query rewritingBM25 · PMC-PatientsAVG: 27.42 -> 34.35Improved
train Qwen3-8B with CRAF RL rather than use it untrained for rewritingQwen3-8B rewriter + Qwen3-Embedding · PMC-PatientsAVG: 36.64 -> 39.87Improved
rewrite queries with HuatuoGPT-o1 for dense retrievalQwen3-Embedding · PMC-PatientsAVG: 36.33 -> 35.11Hurt
rewrite queries with CRAF-8BQwen3-Embedding · ReCDS-PPRMRR: 27.05 -> 28.33Mixed
train with RL reward instead of SFT (ablation)CRAF · ReCDS-PARretrieval metricsImproved
add negative sampling and reward components (ablation)CRAF · ReCDS-PARretrieval metricsImproved
increase training data from 0 to 100 percent (ablation)CRAF · ReCDS-PARretrieval metricsMixed

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