Knowledge Graph-Enhanced Large Language Models via Path Selection
Open accessAbstract
Large Language Models (LLMs) have shown unprecedented performance in various realworld applications.However, they are known to generate factually inaccurate outputs, a.k.a. the hallucination problem.In recent years, incorporating external knowledge extracted from Knowledge Graphs (KGs) has become a promising strategy to improve the factual accuracy of LLM-generated outputs.Nevertheless, most existing explorations rely on LLMs themselves to perform KG knowledge extraction, which is highly inflexible as LLMs can only provide binary judgment on whether a certain knowledge (e.g., a knowledge path in KG) should be used.In addition, LLMs tend to pick only knowledge with direct semantic relationship with the input text, while potentially useful knowledge with indirect semantics can be ignored.In this work, we propose a principled framework KELP with three stages to handle the above problems.Specifically, KELP is able to achieve finer granularity of flexible knowledge extraction by generating scores for knowledge paths with input texts via latent semantic matching.Meanwhile, knowledge paths with indirect semantic relationships with the input text can also be considered via trained encoding between the selected paths in KG and the input text.Experiments on real-world datasets validate the effectiveness of KELP. 1 Input: Verify this claim.Is this claim true or false?Context: ["Akita Prefecture", "specialty", "Akita Inu"] Claim: Akita Prefecture is located in Japan.Output: True.√ Input: Verify this claim.Is this claim true or false?Context: ["Akita Prefecture", "locate", "Japan"] Claim:
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
EPR enumerates all possible paths from an entity to every reachable node within the graph or subgraph, capturing diverse reasoning chains but potentially introducing query-irrelevant information that adds noise to LLM reasoning.
“EPR[65] enumerates all possible paths from an entity 𝑣 ( 𝑞 ) 𝑖 ∈ 𝜖 𝑞 to every reachable node within the graph or subgraph. It captures diverse reasoning chains, providing additional context for LLMs, although it may introduce information that is not related to the query, potentially adding noise to the reasoning process of the LLMs.”
From LEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration (2025) · cites this paper as [65]
Section 3.1 says KELP extracts paths starting from question entities, and Section 3.3 says selecting paths helps avoid excessive, irrelevant context. But the paper describes KELP rather than EPR, and its extraction is limited to one- and two-hop paths; it does not support the claim that EPR enumerates every path to every reachable node. (LLM, conf=0.82)
Experimental — accuracy not yet measuredDomain-specific fine-tuning can further enhance these models' performance, though it comes at an additional cost.
“Domain-specific fine-tuning can further enhance these models' performance [45, 65, 71, 72], though it comes at an additional cost.”
From LEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration (2025) · cites this paper as [65]
Section 5.1 (page unavailable) describes fine-tuning for downstream tasks as laborious, supporting the additional-cost point. It does not say that domain-specific fine-tuning further improves model performance; the paper instead discusses prompt engineering and knowledge-graph path selection. (LLM, conf=0.78)
Experimental — accuracy not yet measuredExisting GraphRAG studies have demonstrated the potential of integrating graph data management techniques with GraphRAG.
“Existing GraphRAG studies [22, 45, 50, 65, 71, 72, 74, 98] have demonstrated the potential of integrating graph data management techniques with GraphRAG.”
From LEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration (2025) · cites this paper as [65]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 17
- Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wen- liang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al. 2023. A multi- task, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023. · arXiv
- Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In NeurIPS.
- Xiaojun Chen, Shengbin Jia, and Yang Xiang. 2020. A review: Knowledge reasoning over knowledge graph. Expert Systems with Applications.
- Jinhao Jiang, Kun Zhou, Xin Zhao, and Ji-Rong Wen. 2023b. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowl- edge graph. In ICLR.
- Jiho Kim, Yeonsu Kwon, Yohan Jo, and Edward Choi. 2023a. KG-GPT: A general framework for reasoning on knowledge graphs using large language models. In EMNLP.
- Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In ICLR.
- Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text trans- former. JMLR.
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and effi- cient foundation language models. arXiv preprint arXiv:2302.13971. · arXiv
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS, volume 30.
- Siyuan Wang, Zhongyu Wei, Jiarong Xu, Taishan Li, and Zhihao Fan. 2023. Unifying structure reasoning and language model pre-training for complex reason- ing. arXiv preprint arXiv:2301.08913. · arXiv
- Song Wang, Zhen Tan, Ruocheng Guo, and Jundong Li. 2023a. Noise-robust fine-tuning of pretrained language models via external guidance. In EMNLP.
- Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, et al. 2023b. Knowledge editing for large language models: A survey. arXiv preprint arXiv:2310.16218. · arXiv
- Yaqing Wang, Song Wang, Yanyan Li, and Dejing Dou. 2022. Recognizing medical search query intent by few-shot learning. In Proceedings of the 45th Inter- national ACM SIGIR Conference on Research and Development in Information Retrieval, pages 502- 512.
- Yaqing Wang, Song Wang, Quanming Yao, and Dejing Dou. 2021b. Hierarchical heterogeneous graph repre- sentation learning for short text classification. CoRR, abs/2111.00180. · arXiv
- Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emer- gent abilities of large language models. TMLR.
- Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, et al. 2024. Usable xai: 10 strategies towards exploiting explainability in the llm era. arXiv preprint arXiv:2403.08946. · arXiv
- Yaochen Zhu, Liang Wu, Qi Guo, Liangjie Hong, and Jundong Li. 2024. Collaborative large language model for recommender systems. In WWW, pages 3162-3172.
Cited by
Sorted by citations
KoSEL: Knowledge subgraph enhanced large language model for medical question answering
Zeng, Z., Cheng, Q., Hu, X., Zhuang, Y., Liu, X., He, K., & Liu, Z. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112837 · Cited by 45 · see citing works
Practices, opportunities and challenges in the fusion of knowledge graphs and large language models
Cai, L., Yu, C., Kang, Y., Fu, Y., Zhang, H., & Zhao, Y. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1590632 · Cited by 30 · see citing works
Hua, Y., Li, K., Wang, R., Li, Y., Wang, G., & Yan, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103613 · Cited by 18 · see citing works
FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
Gao, Z., Cao, Y., Wang, H., Ke, A., Feng, Y., Zhou, S. K., & Xie, X. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.321 · Cited by 17 · see citing works
SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
Cai, Y., Guo, Z., Pei, Y., Bian, W., & Zheng, W. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.163 · Cited by 14 · see citing works
Knowledge graph reasoning: Mainstream methods, applications and prospects
Liu, H., Yang, S., Shi, G., & Miao, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111625 · Cited by 12 · see citing works
Self-citationLEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration
Cao, Y., Gao, Z., Li, Z., Xie, X., Zhou, S. K., & Xu, J. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3748191.3748194 · Cited by 11 · see citing works
A knowledge-graph-based pharmaceutical engineering chatbot for drug discovery
Taskiran, N. P., Tsai, C.-E. J., Huang, S., Chakraborty, A., & Venkatasubramanian, V. (2025) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2025.109318 · Cited by 11 · see citing works
Bridging data and discovery: a survey on knowledge graphs in AI for science
Ding, K., Zhu, Z., Tang, Y., Feng, K., Zhuang, X., Yang, Y., Yang, Y., Du, H., Ni, Z., Wang, S., et al. (2026) · National Science Review · doi:10.1093/nsr/nwag140 · Cited by 8 · see citing works
Self-citationIgnatowicz, J., Kutt, K., & Nalepa, G. J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228881 · Cited by 6 · see citing works
Ren, J. F., Li, B., Xu, Z., Zhang, X., Fayek, H. M., & Li, X. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792358 · Cited by 5 · see citing works
Bringing Two Worlds Together: The Convergence of Large Language Models and Knowledge Graphs
Cai, L., Kang, Y., Yu, C., Fu, Y., Zhang, H., & Zhao, Y. (2024) · International Conference on Automation, Robotics and Computer Engineering (ICARCE) · doi:10.1109/icarce63054.2024.00046 · Cited by 5 · see citing works
Large Language Model and Knowledge Graph Entangled Logical Reasoning
Xu, Z., Li, J., & Zhang, W. (2024) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg63256.2024.00061 · Cited by 5 · see citing works
Self-citationWang, K., Yan, S., Liu, Z., Yuan, X., Li, F., Jiang, B., Yang, S., & Deng, H. (2025) · Electronics · doi:10.3390/electronics14214138 · Cited by 3 · see citing works
Hou, J., Li, Y., & Qiang, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-32657-9 · Cited by 2 · see citing works
Ahmad, A. (2024) · Conference on AI, Science, Engineering, and Technology (AIxSET) · doi:10.1109/aixset62544.2024.00050 · Cited by 1 · see citing works
SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Querying
Lee, S., Park, S., & Han, W.-S. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.883 · Cited by 1 · see citing works
Ding, H., Chao, Y., Li, X., Chen, X., Kong, X., & Zhang, X. (2025) · International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) · doi:10.1109/icbaie66852.2025.11326597 · Cited by 1 · see citing works
Enhancing Large Language Models Reasoning via Multi-Path Optimization on Knowledge Graph
Liao, J., Liu, C., Ding, Y., Wang, H., Tang, Z., Li, K., & Li, K. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3682046 · Cited by 1 · see citing works
Neurosymbolic Large Language Models: A Survey of Symbolic Integration, Reasoning and Explainability
Rani, M., Mishra, B. K., & Thakker, D. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10794-4 · Cited by 1 · see citing works
KGE: Expert Model-Based Domain-Specific Question Answering MethodPreprint
Li, Z., Li, D., Yang, Y., Sun, L., An, D., & Yang, Q. (2025) · doi:10.36227/techrxiv.176148622.29018466/v1
Exploring Multi-aspect Information for Knowledge Graph Completion with Large Language Model
Wang, L., Sheng, J., Zhang, W., Liu, T., & Zhang, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227427
Construction Method of Campus Safety Knowledge Graph Based on Retrieval-Augmented
Yang, W., Li, S., Li, J., & Shi, Y. (2026) · Electronics · doi:10.3390/electronics15091826
Self-citationDynamic Evaluation of Impact of Contextual Knowledge Graphs on Large Language Model Performance
Tyagi, R., Thakur, A., Verma, P., Abdullah, O. F., Jasim, S. W., & Kiran, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18913-4_24
Approaching LLM Alignment using Agents with RAG
Fliahin, V., Turuta, O., & Turuta, O. (2026) · International Workshop of IT-professionals on Artificial Intelligence (ProfIT AI) · doi:10.55056/ceur-ws.org/vol-4164/short6.pdf
Li, X., Feng, W., Lu, Y., Koh, J., Choi, E., Chen, J., He, J., & Ngiam, K. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3441-7_39
Clue-RAG: Towards Accurate and Cost-Efficient Graph-Based RAG Via Multi-Partite Graph-Based Index
Su, Y., Fang, Y., Zhou, Y., & Yang, C. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00179
Jurmu, M., Naumanen, M., Westerstrand, S., Lämsä, A., Myllymaa, K., & Ailisto, H. J. (2026) · Applied Artificial Intelligence · doi:10.1080/08839514.2026.2721301
Wang, S., & Jia, X. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833604
Self-citationGTAP: Graph Topology-Aware Pre-Training for Graph Classification
Hu, C., & Zhang, Z. (2026) · Electronics · doi:10.3390/electronics15194390
MapGPT: Natural Language Interface for Geo-Spatial Queries on Vector Maps
Charishma, G., Ramudu, B., P., R. K., Alampatta, S., & Panigrahi, N. (2026) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct68978.2026.11700682
Introspective Dynamic Strategy for Knowledge Graph Enhanced Reasoning in Large Language Models
Duan, J., Chen, Q., Wang, Z., Gao, Z., Huang, H., & Yang, W. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716510
Retrieval-Augmented Knowledge Completion for Graph-Constrained Reasoning
Xu, W., Fan, M., Zhou, W., Ma, C., Liu, X., & Xiong, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729959
Huang, L., Chen, W., Yu, S., Deng, C., & Sun, B. (2026) · Applied Sciences · doi:10.3390/app162010394
Тұрсынхан, А., Turdalyuly, M., Yerimbetova, A., Akmetov, B., & Sakenov, B. (2026) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk71847.2026.11745148
Knowledge Graphs for Tracing Conceptual Understanding in Programming Education
Wang, T., & Zhang, D. (2026) · doi:10.1109/icaie70080.2026.11751382
Design of Artificial Intelligence Service Foundation for Power Market Trading Platform
Shao, P., Xie, W., Ji, S., Deng, Y., & Zhao, Q. (2026) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec67763.2026.11750767
- Authors
- Liu, H., Wang, S., Zhu, Y., Dong, Y., & Li, J.
- Affiliations
- University of Virginia (US)
- Venue
- Findings of the Association for Computational Linguistics ACL 2024
- Published
- 2024
- Pages
- 6311-6321
- OpenAlex
- W4402683926
- Cited by
- 28
- References
- 0
- Citations by year
- 2026: 15 · 2025: 9 · 2024: 4
- FWCI
- 8.28
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- Funders
- National Science Foundation (2223769, 2144209, 2228534, 2154962, 2006844)
- Cisco Systems
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Keywords
- knowledge graphs, large language models, hallucinations, factual accuracy, knowledge extraction, claim verification, kelp
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
