AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning

Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Zhongyuan Wang, Jichen Zhang, Shirui Pan, Xindong Wu

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs

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 knowledge encoder (GNN structural representations) (ablation)KRLM · FB-V1 (E2E)Hit@10: 0.614 -> 0.705Improved
add knowledge decoder (structure-constrained projection head) (ablation)KRLM · FB-V1 (E2E)Hit@10: 0.674 -> 0.705Improved
add knowledge memory in KRL attention (ablation)KRLM · FB-V1 (E2E)Hit@10: 0.691 -> 0.705Improved
use PAA instead of mean pooling for word-level embeddings (ablation)KRLM · FB-V1 (E2E)Hit@10: 0.692 -> 0.705Improved
add KRL distillation loss (ablation)KRLM · NL-0 (E2E)Hit@10: 0.554 -> 0.591Improved
add KL divergence term in loss (ablation)KRLM · WN-V1 (E2E)Hit@10: 0.798 -> 0.801No clear effect
add KL term in loss (other datasets) (ablation)KRLM · NL-0 (E2E)Hit@10: 0.533 -> 0.591Improved
fine-tune pretrained KRLM on target dataset vs zero-shotKRLM · IndE (12 datasets avg)Hit@10: 0.738 -> 0.751Improved
KRLM vs best prior KGFM/LLM-based baselinesKRLM (FT) · IndER (13 datasets avg)Hit@10: 0.542 -> 0.556Improved
KRLM transductive training vs MKGL/CSProm-KGKRLM (E2E) · FB15k-237 / WN18RR (transductive)Hit@10: 0.568 vs 0.591 (FB15k-237); 0.659 vs 0.678 (WN18RR)Hurt
increase knowledge memory size K beyond 50 (ablation)KRLM · hyperparameter analysisHit@10No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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