# Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

arXiv: https://arxiv.org/abs/2405.01649 · HTML: https://mlsanity.com/paper/2405.01649/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 2 May 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities](https://mlsanity.com/paper/2305.13168/) (2023)
- [Making Large Language Models Perform Better in Knowledge Graph Completion](https://mlsanity.com/paper/2310.06671/) (2023)
- [Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning](https://mlsanity.com/paper/2402.10738/) (2024)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)
- [Logical Message Passing Networks with One-hop Inference on Atomic Formulas](https://mlsanity.com/paper/2301.08859/) (2023)
- [Complex Logical Reasoning over Knowledge Graphs using Large Language Models](https://mlsanity.com/paper/2305.01157/) (2023)
- [ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2309.01538/) (2023)
- [Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs](https://mlsanity.com/paper/2404.04264/) (2024)
- [Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese](https://mlsanity.com/paper/2309.04175/) (2023)
- [Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors](https://mlsanity.com/paper/2304.07063/) (2023)
- [Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs](https://mlsanity.com/paper/2305.13585/) (2023)
- [POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2401.05596/) (2024)

## Built on by (most cited first, 10 of 10)

- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [GraSP: Graph-Structured Skill Compositions for LLM Agents](https://mlsanity.com/paper/2604.17870/) (2026)
- [Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training](https://mlsanity.com/paper/2602.22576/) (2026)
- [Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression](https://mlsanity.com/paper/2505.13527/) (2025)
- [AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents](https://mlsanity.com/paper/2602.14257/) (2026)
- [An Alternative Trajectory for Generative AI](https://mlsanity.com/paper/2603.14147/) (2026)
- [Intention Collapse: Intention-Level Metrics for Reasoning in Language Models](https://mlsanity.com/paper/2601.01011/) (2026)
- [Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables](https://mlsanity.com/paper/2605.25985/) (2026)
- [Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling](https://mlsanity.com/paper/2605.27023/) (2026)
- [CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion](https://mlsanity.com/paper/2609.08244/) (2026)

## Abstract (arXiv)

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.