# CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering

arXiv: https://arxiv.org/abs/2409.19753 · HTML: https://mlsanity.com/paper/2409.19753/

## Key facts

- Cited by 17 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 2 of its 59 references that are in the map.
- First posted on arXiv 29 Sep 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 2 of 2)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)

## Built on by (most cited first, 17 of 17)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2502.10455/) (2025)
- [Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness](https://mlsanity.com/paper/2504.05163/) (2025)
- [DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.10198/) (2025)
- [TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG](https://mlsanity.com/paper/2412.05447/) (2024)
- [Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation](https://mlsanity.com/paper/2505.11754/) (2025)
- [RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.08862/) (2025)
- [KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering](https://mlsanity.com/paper/2512.10999/) (2025)
- [Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks](https://mlsanity.com/paper/2505.16849/) (2025)
- [Decomposing and Revising What Language Models Generate](https://mlsanity.com/paper/2509.00765/) (2025)
- [Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling](https://mlsanity.com/paper/2602.21728/) (2026)
- [DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment](https://mlsanity.com/paper/2603.20059/) (2026)
- [GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering](https://mlsanity.com/paper/2605.29584/) (2026)
- [On the Influence of Shape, Texture and Color for Learning Semantic Segmentation](https://mlsanity.com/paper/2410.14878/) (2024)
- [Contrast All the Time: Learning Time Series Representation from Temporal Consistency](https://mlsanity.com/paper/2410.15416/) (2024)
- [Evaluating and Improving Graph to Text Generation with Large Language Models](https://mlsanity.com/paper/2501.14497/) (2025)
- [Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement](https://mlsanity.com/paper/2604.14749/) (2026)

## Abstract (arXiv)

Recent studies have explored the use of Large Language Models (LLMs) with Retrieval Augmented Generation (RAG) for Knowledge Graph Question Answering (KGQA). They typically require rewriting retrieved subgraphs into natural language formats comprehensible to LLMs. However, when tackling complex questions, the knowledge rewritten by existing methods may include irrelevant information, omit crucial details, or fail to align with the question's semantics. To address them, we propose a novel rewriting method CoTKR, Chain-of-Thought Enhanced Knowledge Rewriting, for generating reasoning traces and corresponding knowledge in an interleaved manner, thereby mitigating the limitations of single-step knowledge rewriting. Additionally, to bridge the preference gap between the knowledge rewriter and the question answering (QA) model, we propose a training strategy PAQAF, Preference Alignment from Question Answering Feedback, for leveraging feedback from the QA model to further optimize the knowledge rewriter. We conduct experiments using various LLMs across several KGQA benchmarks. Experimental results demonstrate that, compared with previous knowledge rewriting methods, CoTKR generates the most beneficial knowledge representation for QA models, which significantly improves the performance of LLMs in KGQA.