Lune

WWW2026Top-tier venue

A Unified Framework for Rule Learning: Integrating Commonsense Knowledge from LLMs with Structured Knowledge from Knowledge Graphs

Qirui Hao, Kewei Cheng, Tongze Zhang, Hongyuan Liu, Junming Shao, Carl Yang

Abstract

Unlike many black-box machine learning models, logical rules offer human-understandable explanations for decision-making processes, which is especially important in transparency-critical domains like finance and healthcare. Traditional rule learning methods primarily rely on structured knowledge from Knowledge Graphs (KGs), which cannot align the learned rules with commonsense reasoning, leading to potentially incorrect rules. While Large Language Models (LLMs) offer rich commonsense knowledge, they are prone to hallucinations, which hinder their reliability in learning logical rules. The structured knowledge in KGs can serve as an external reference to mitigate these hallucinations. To leverage the strengths of both approaches, we propose a unified framework CSRL to integrate the commonsense knowledge of LLMs with the structured knowledge from KGs for logical rule learning. CSRL achieves a seamless integration of these two types of knowledge. On one hand, it samples multiple instances of each rule based on the KG structure and exploits LLMs to check the reliability of a rule based on such multiple cases, thereby effectively reducing the effect of hallucinations. On the other hand, CSRL utilizes commonsense knowledge from LLMs to guide dynamic and efficient sampling of useful path instances within KGs. Extensive results from quantitative KG completion experiments and qualitative LLM/human-based semantic assessments demonstrate that our algorithm not only performs well on reasoning tasks but also offers greater reliability and alignment with the real world. Our source code is available at: https://github.com/PerseidsMeteorShower/CSRL .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Large Language Models as Commonsense Knowledge for Large-Scale Task Planning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Multitask Prompted Training Enables Zero-Shot Task Generalization
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on22

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Multitask Prompted Training Enables Zero-Shot Task GeneralizationVictor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach et al.ICLR 2022 · 1,976 citations
  3. Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
  4. (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge GraphsJena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da et al.AAAI 2021 · 458 citations
  5. Large Language Models as Commonsense Knowledge for Large-Scale Task PlanningZirui Zhao, Wee Sun Lee, David HsuNeurIPS 2023 · 423 citations

Related papers

  1. Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question AnsweringYixin Ji, Kaixin Wu, Juntao Li, Wei Chen et al.EMNLP Findings 2024 · 17 citations
  2. Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge GraphsYuxin Shi, Han Fu, Zhuo Li, Chenghao Liu et al.ICLR 2026
  3. Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward ModelingShiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao et al.ICLR 2026 · 3 citations
  4. Neural Compositional Rule Learning for Knowledge Graph ReasoningKewei Cheng, Nesreen K. Ahmed, Yizhou SunICLR 2023 · 15 citations
  5. Transfer Rule Learning over Large Knowledge GraphsHong Liu, Zhe Wang, Kewen Wang, Xiaowang Zhang et al.WWW 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines