面向安全环保领域的知识图谱增强大模型探讨
Journal: Advances in Computer and Autonomous Intelligence Research DOI: 10.12238/acair.v3i1.11916
Abstract
为解决钢铁企业安环领域数智化实施过程中存在的信息透明度不足、传递不及时、数据难以分析以及分析结果难以被业务人员理解等问题,引入能深度理解和应用安全和环保领域内的专业知识,提供准确和专业的信息,为复杂问题提供专业回答和解决方案大语言模型。然而,大模型自身面临解释性不足、知识实时性差、生成结果存在虚假信息等诸多挑战。知识图谱作为一种结构化的知识模型,其真实性和可靠性,成为提高大模型解释和推理能力的有力工具。因此结合二者的优势,本文探讨知识图谱增强大模型几个方向,为安环领域的数智发展提供参考。
Keywords
钢铁企业；安环领域；数智化；大语言模型；知识图谱
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] Zhaojun Q,Yuqian L.A Knowledge Graph-based knowled ge representation for adaptive manufacturing control under mass personalization[J].Manufacturing Letters,2023,35(S):96-104.
[2] Gajewski,Indurkhya.An Approach to Task Representation Based on Object Features and Affordances[J].SENSORS,2022,22(16):615.
[3] Zhong Z,Chen D.A Frustratingly Easy Approach for Joint Entity and Relation Extraction[J].2020.
[4] Nan G,Guo Z,Sekulići, et al. Reasoning with latent struc ture refinement for document-level relation extraction[J].arXiv:2005.06312,2020.
[5] Peng H,Gang Z,Yao Y, et al. A type-augmented knowledge graph embedding framework for knowledge graph completion [J].Scientific reports,2023,13(1):12364-12364.
[6] Li J,Su X. Transerr: translation-based knowledge graph completion via efficient relation rotation[J].arXiv:2306.14580,2023.
[7] Nickel M, Tresp V, Kriegel H P. A three-way model for collective learning on multi-relational data[C]//Proceedings of the International Conference on Machine Learning, c2011:809-816.
[8] Yu M, Guo J, Yu J, et al. BDRI: block decomposition based on relational interaction for knowledge graph completion[J]. Data Mining and Knowledge Discovery,2023,37(2):767-787.
[9] Sui Y,He Y, Liu N, et al. FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering [J].arxiv preprint arxiv:2405.13873,2024.
[10] Guo T, Yang Q, Wang C, et al. Knowledge navigator: Leveraging large language models for enhanced reasoning over knowledge graph[J].Complex & Intelligent Systems,2024:1-14.
[11] YAO S Y,YU D,ZHAO J,et al.Tree of thoughts: Deliberate problem solving with large language models[J]. Advances in Neural Information Processing Systems,2024,36:11809-11822.
[12] BESTA M, BLACH N, KUBICEK A, et al. Graph of thoughts: Solving elaborate problems with large language models[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024,38(16):17682-17690.
[13] GUAN Z H,WU Z H, LIU Z L, et al. CohortGPT: An enhanced GPT for participant recruitment in clinical study [EB/OL]. 2023:arXiv:2307.11346.http: //arxiv.org/ abs/2307.11346.
[14] TURPIN M, MICHAEL J, PEREZ E, et al. Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting[EB/OL]. 2023: arXiv: 2305.04388.http: //arxiv.org/abs/2305.04388.
[15] SUN Y Q, SHI Q, QI L, et al. JointLK: Joint reasoning with language models and knowledge graphs for common⁃ sense question answering[EB/OL].2021:arXiv:2112.02732.
[16] YASUNAGA M,REN H Y,BOSSELUT A,et al.QAGNN: Reasoning with language models and knowledge graphs for question answering[EB/OL].2021:arXiv:2104.06378.http://arxiv.org/abs/2104.06378.
[2] Gajewski,Indurkhya.An Approach to Task Representation Based on Object Features and Affordances[J].SENSORS,2022,22(16):615.
[3] Zhong Z,Chen D.A Frustratingly Easy Approach for Joint Entity and Relation Extraction[J].2020.
[4] Nan G,Guo Z,Sekulići, et al. Reasoning with latent struc ture refinement for document-level relation extraction[J].arXiv:2005.06312,2020.
[5] Peng H,Gang Z,Yao Y, et al. A type-augmented knowledge graph embedding framework for knowledge graph completion [J].Scientific reports,2023,13(1):12364-12364.
[6] Li J,Su X. Transerr: translation-based knowledge graph completion via efficient relation rotation[J].arXiv:2306.14580,2023.
[7] Nickel M, Tresp V, Kriegel H P. A three-way model for collective learning on multi-relational data[C]//Proceedings of the International Conference on Machine Learning, c2011:809-816.
[8] Yu M, Guo J, Yu J, et al. BDRI: block decomposition based on relational interaction for knowledge graph completion[J]. Data Mining and Knowledge Discovery,2023,37(2):767-787.
[9] Sui Y,He Y, Liu N, et al. FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering [J].arxiv preprint arxiv:2405.13873,2024.
[10] Guo T, Yang Q, Wang C, et al. Knowledge navigator: Leveraging large language models for enhanced reasoning over knowledge graph[J].Complex & Intelligent Systems,2024:1-14.
[11] YAO S Y,YU D,ZHAO J,et al.Tree of thoughts: Deliberate problem solving with large language models[J]. Advances in Neural Information Processing Systems,2024,36:11809-11822.
[12] BESTA M, BLACH N, KUBICEK A, et al. Graph of thoughts: Solving elaborate problems with large language models[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024,38(16):17682-17690.
[13] GUAN Z H,WU Z H, LIU Z L, et al. CohortGPT: An enhanced GPT for participant recruitment in clinical study [EB/OL]. 2023:arXiv:2307.11346.http: //arxiv.org/ abs/2307.11346.
[14] TURPIN M, MICHAEL J, PEREZ E, et al. Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting[EB/OL]. 2023: arXiv: 2305.04388.http: //arxiv.org/abs/2305.04388.
[15] SUN Y Q, SHI Q, QI L, et al. JointLK: Joint reasoning with language models and knowledge graphs for common⁃ sense question answering[EB/OL].2021:arXiv:2112.02732.
[16] YASUNAGA M,REN H Y,BOSSELUT A,et al.QAGNN: Reasoning with language models and knowledge graphs for question answering[EB/OL].2021:arXiv:2104.06378.http://arxiv.org/abs/2104.06378.
Copyright © 2025 明平寿, 杨恒, 兰弄, 文志强, 皮理想, 周本胜, 袁怀月
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
