AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models

Yu Liu, Xixun Lin, Yanmin Shang, Yangxi Li, Shi Wang, Yanan Cao

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 2 citations (OpenAlex)

Read the paper

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 path prioritization module (ablation)PathMind · CWQHits@1: 0.643 -> 0.707Improved
add path prioritization module (ablation)PathMind · WebQSPHits@1: 0.840 -> 0.895Improved
add path-wise preference alignment (DPO) (ablation)PathMind · CWQHits@1: 0.672 -> 0.707Improved
add path-wise preference alignment (DPO) (ablation)PathMind · WebQSPHits@1: 0.871 -> 0.895Improved
add two-phase training (SFT + DPO) (ablation)PathMind · CWQF1: 0.274 -> 0.614Improved
use important (prioritized) paths instead of shortest paths (ablation)PathMind · CWQHits@1: 0.662 -> 0.707Improved
use important paths instead of random paths (ablation)PathMind · WebQSPHits@1: 0.356 -> 0.895Improved
increase top-K node selection beyond 3 (ablation)PathMind · WebQSP and CWQF1Hurt
switch backbone from Llama3.1-8B to Llama2-7B (ablation)PathMind · WebQSPHits@1: 0.895 -> 0.864Hurt
switch backbone from Llama3.1-8B to Qwen2-7B (ablation)PathMind · CWQHits@1: 0.707 -> 0.665Hurt
single-pass reasoning over prioritized paths vs iterative synergy methodsPathMind · WebQSP# input tokens: 7,069 -> 216Improved

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