AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs

Yisen Gao, Jiaxin Bai, Tianshi Zheng, Ziwei Zhang, Qingyun Sun, Xingcheng Fu, Jianxin Li, Yangqiu Song

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 10 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 reinforcement learning on top of supervised training (ablation)CtrlHGen · WN18RR (pattern condition)condition adherence accuracy: 81.5 -> 93.5Improved
add reinforcement learning on top of supervised training (ablation)CtrlHGen · WN18RR (pattern condition)Jaccard: 71.5 -> 77.0Improved
add Dice and Overlap rewards alongside Jaccard (ablation)CtrlHGen · WN18RR (pattern condition)condition adherence accuracy: 90.3 -> 93.5Improved
add Dice and Overlap rewards alongside Jaccard (ablation)CtrlHGen · WN18RR (pattern condition)Jaccard: 74.8 -> 77.0Improved
add condition-adherence reward (ablation)CtrlHGen · WN18RR (pattern condition)condition adherence accuracy: 68.3 -> 93.5Improved
add condition-adherence reward (ablation)CtrlHGen · WN18RR (pattern condition)Jaccard: 77.5 -> 77.0Hurt
add sub-logical decomposition data augmentation (ablation)CtrlHGen · DBpedia50 (13 logical patterns)JaccardImproved
add sub-logical decomposition data augmentation (ablation)CtrlHGen · DBpedia50 (13 logical patterns)condition adherence accuracyNo clear effect
use sub-logic decomposition instead of Logic-Gen augmentationCtrlHGen · DBpedia50 (pattern condition, SFT only)condition adherence accuracy: 65.9 -> 73.1Improved
use sub-logic decomposition instead of Logic-Gen augmentationCtrlHGen · DBpedia50 (pattern condition, SFT only)Jaccard: 69.5 -> 70.1Improved
add control conditions (pattern) to AbductiveKGRCtrlHGen · FB15k-237Jaccard: 61.4 -> 65.5Improved
replace GPT5(Thinking) with CtrlHGenCtrlHGen · FB15k-237 (avg of five conditions)Jaccard: 18.7 -> 64.3Improved

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