AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA

Changhao Wang, Yanfang Liu, Xinxin Fan, Ao Tian, Lanzhi Zhou, Yunfeng Lu

ICML 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 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 few-shot question classifier routing to dual-track branches versus only fact verification (ablation)DTKG · CWQACC: 86.0 -> 90.0Improved
add classifier routing versus only chained reasoning branch (ablation)DTKG · MintakaEM: 57.0 -> 67.6Improved
use accurate classifier instead of random branch assignment (ablation)DTKG · HotpotQAACC: 73.0 -> 85.8Improved
add reranker stage to cosine-similarity scoring (two-stage scoring) (ablation)DTKG · HotpotQAACC: 77.5 -> 85.8Improved
add cosine prefilter to reranker-only scoring (ablation)DTKG · HotpotQAACC: 80.2 -> 85.8Improved
add two-stage scoring versus random relation selection (ablation)DTKG · HotpotQAACC: 58.2 -> 85.8Improved
add generic rule-based denoising (ablation)DTKG · CWQACC: 75.8 -> 84.6Improved
use task-aware LLM denoising instead of generic denoising (ablation)DTKG · CWQACC: 84.6 -> 90.0Improved
add task-aware denoising on QALD10-en (ablation)DTKG · QALD10-enEM: 49.8 -> 50.0No clear effect
use DTKG instead of ToG path exploration on parallel-heavy datasetLlama 3 8B · MintakaEM: 58.5 -> 67.6Improved
use DTKG instead of CoT on GraphRAG-BenchLlama 3 8B · GraphRAG-BenchEM: 14.4 -> 14.5No clear effect

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