面向国际事件分析的大模型问答系统综述

doi:10.3969/j.issn.1006-2475.2025.03.005

摘要/Abstract

摘要： 大模型作为当前人工智能研究的核心焦点，展现出了强大的跨领域理解和生成能力，并在包括事件分析在内的众多领域中广泛应用，以其卓越的性能推动了智能问答系统的革新与发展。尽管大模型在一般问答场景中展现出强大的处理能力，但在应对具有深度专业背景和高度动态性的影响国际关系的国际事件时仍面临挑战。近些年有不少学者对垂直领域大模型问答和国际关系的定量分析系统进行了深入研究，但是对于两者结合的交叉领域的文献综述还不多。为了给面向国际事件分析的大模型问答系统的开发者和研究者提供全面的框架参考，首先，从早期的国际事件分析系统入手，结合国际事件分析的实际需求，分析各类通用大模型在此任务下的适用性。然后，参考金融、教育、医学、法律等领域成功案例，提炼出构建国际事件分析专用大模型问答系统的策略，系统梳理与该任务紧密相关的公开数据集资源。最后，深度剖析当前的瓶颈与未来发展方向。

关键词: 垂直领域大模型, 国际事件分析, 大模型问答系统, 事件发现, 事件预测

Abstract: As the core focus of current artificial intelligence research， large language models have demonstrated strong cross-domain understanding and generation capabilities. They are widely used in many fields including event analysis， and promote the innovation and development of intelligent question answering system with its excellent performance. Although large language models show strong processing ability in general Q&A scenarios， they still face challenges in dealing with international events with deep professional backgrounds and high dynamics that affect international relations. In recent years， many scholars have focused on domain-specific large language models and quantitative analysis system for international relations， but there are few literature reviews on the cross-field of the combination of the two. In order to provide a comprehensive framework for developers and researchers of large language model question answering systems for international event analysis. Firstly， starting from the early international event analysis system， combined with the actual needs of international event analysis， the applicability of various general large language models in this task is analyzed. Secondly， by referring to the successful cases in the fields of finance， education， medicine， law， etc.， the strategy of constructing the domain-specific large-model question-and-answer system for international event analysis is extracted. In addition， the open data set resources closely related to the task are systematically combed. Finally， the current bottleneck and the future development direction are deeply analyzed.

Key words: , domain-specific large language model； analysis of international events； large language model Q&, A system； event detection； event prediction

中图分类号:

TP182

雷霁月, 苏鹏, 聂芸, 林川. 面向国际事件分析的大模型问答系统综述[J]. 计算机与现代化, 2025, 0(03): 29-37.

LEI Jiyue, SU Peng, NIE Yun, LIN Chuan. Review of Large Language Model Question Answering Systems for International Event Analysis[J]. Computer and Modernization, 2025, 0(03): 29-37.

参考文献

［1］ QIU X P， SUN T X， XU Y G， et al. Pre-trained models for natural language processing： A survey［J］. Science China Technological Sciences， 2020，63（10）：1872-1897.
［2］ SU J， JIANG C F， JIN X， et al. Large Language Models for Forecasting and Anomaly Detection： A Systematic Literature Review［EB/OL］. （2024-02-20）［2024-04-26］. https：//arxiv.org/abs/2402.10350.
［3］ ZHOU H， YIN H P， ZHENG H Y， et al. A survey on multi-modal social event detection［J］. Knowledge-Based Systems， 2020，195（3）. DOI： 10.1016/j.knosys.2020.105695.
［4］ JI S X， PAN S R， CAMBRIA E， et al. A survey on knowledge graphs： Representation， acquisition， and applications［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021，33（2）：494-514.
［5］张亚明，宋雯婕，刘海鸥，等. 学科交叉视域下国际舆论场突发公共卫生事件网络舆情传播研究综述［J］. 现代情报， 2023，43（4）：165-176.
［6］庞珣. 国际关系研究的定量方法：定义、规则与操作［J］. 世界经济与政治， 2014（1）：5-25.
［7］张雪. 事件数据库在国际关系研究中的应用［D］. 北京：外交学院， 2023.
［8］卢凌宇，张传基. 浅析国际政治大数据预测的限度［J］. 欧洲研究， 2021，39（4）：130-154.
［9］ LEISEROWITZ A. International public opinion， perception， and understanding of global climate change［J］. Human development report， 2007，2008（2007）：31-70.
［10］ LIPPERT T H， LIPPERT T H. Taking stock of the situation： NATO［M］// NATO， Climate Change， and International Security. 2019：47-79.
［11］ GORDON J， VAN DURME B， SCHUBERT L K. Learning from the Web： Extracting general world knowledge from noisy text［C］// Proceedings of the 2nd AAAI Conference on Collaboratively-built Knowledge Sources and Artificial Intelligence. AAAI， 2010：10-15.
［12］ CHEN X， ZHOU X M， SELLIS T， et al. Social event detection with retweeting behavior correlation［J］. Expert Systems with Applications， 2018，114：516-523.
［13］ CHAMBERS N， JURAFSKY D. Unsupervised learning of narrative event chains［C］// Proceedings of ACL-08： HLT. ACL， 2008：789-797.
［14］ GALLA D， BURKE J. Predicting social unrest using GDELT［C］// International Conference on Machine Learning and Data Mining in Pattern Recognition. Springer， 2018：103-116.
［15］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［J］. Advances in Neural Information Processing Systems， 2017，30：5998-6008.
［16］ KENTON J D M W C， TOUTANOVA L K. BERT： Pre-training of deep bidirectional transformers for language understanding［C］// Proceedings of NAACL-HLT. ACL， 2019：4171-4186.
［17］ YANG S， FENG D W， QIAO L B， et al. Exploring pre-trained language models for event extraction and generation［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. ACL， 2019：5284-5294.
［18］ DU X， CARDIE C. Document-level event role filler extraction using multi-granularity contextualized encoding［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. ACL， 2020：8010-8020.
［19］ DING L， CHEN X J， WEI J， et al. Mabert： Mask-attention-based Bert for Chinese event extraction［J］. ACM Transactions on Asian and Low-Resource Language Information Processing， 2023，22（7）：1-21.
［20］ JENKINS C， AGARWAL S， BARRY J， et al. Massively multi-lingual event understanding： Extraction， visualization， and search［C］// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. ACL， 2023：247-256.
［21］ BROWN T， MANN B， RYDER N， et al. Language models are few-shot learners［J］. Advances in Neural Information Processing Systems， 2020，33：1877-1901.
［22］ LIU F. Learning to summarize from human feedback［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. ACL， 2020：1934-1945.
［23］ XIAN Y， SCHIELE B， AKATA Z. Zero-shot learning-the good， the bad and the ugly［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2017：4582-4591.
［24］ HU D Q， LIU B， ZHU X F， et al. Zero-shot information extraction from radiological reports using ChatGPT［J］. International Journal of Medical Informatics， 2024，183：105321.
［25］ TAVENARD R， FAOUZI J， VANDEWIELE G， et al. Tslearn， a machine learning toolkit for time series data［J］. Journal of Machine Learning Research， 2020，21（118）：1-6.
［26］ ZHU C C， CHEN M H， FAN C J， et al. Learning from history： Modeling temporal knowledge graphs with sequential copy-generation networks［J］. AAAI Conference on Artificial Intelligence， 2021，35（5）：4732-4740.
［27］ SHI X M， XUE S Q， WANG K R， et al. Language models can improve event prediction by few-shot abductive reasoning［J］. Advances in Neural Information Processing Systems， 2024，36：1-26.
［28］ ZHANG L， JIJO K， SETTY S， et al. Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately［EB/OL］. （2024-02-01）［2024-04-26］. https：//arxiv.org/abs/2402.01722.
［29］ LINEGAR M， KOCIELNIK R， ALVAREZ R M. Large language models and political science［J］. Frontiers in Political Science， 2023，5：1257092.
［30］ ABID A， FAROOQI M， ZOU J. Persistent anti-muslim bias in large language models［C］// Proceedings of the 2021 AAAI/ACM Conference on AI， Ethics， and Society. ACM， 2021：298-306.
［31］ KENTHAPADI K， LAKKARAJU H， RAJANI N. Generative AI meets responsible AI： Practical challenges and opportunities［C］// Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM， 2023：5805-5806.
［32］ KUKREJA S， KUMAR T， PUROHIT A， et al. A literature survey on open source large language models［C］// Proceedings of the 2024 7th International Conference on Computers in Management and Business. IEEE， 2024：133-143.
［33］ GURURANGAN S， MARASOVIĆ A， SWAYAMDIPTA S， et al. Don’t stop pretraining： Adapt language models to domains and tasks［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. ACL， 2020：8342-8360.
［34］ WU S， IRSOY O， LU S， et al. Bloomberggpt： A Large Language Model for Finance［EB/OL］. （2023-03-14）［2024-04-26］. https：//arxiv.org/abs/2303.17564.
［35］ SMITH J S， KARLINSKY L， GUTTA V， et al. Coda-prompt： Continual decomposed attention-based prompting for rehearsal-free continual learning［C］// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2023：11909-11919.
［36］ LIU M， ENE T D， KIRBY R， et al. Chipnemo： Domain-adapted ll ms for Chip Design［EB/OL］. （2023-10-30）［2024-04-26］. https：//arxiv.org/abs/2311.00176.
［37］ NGUYEN H T. A Brief Report on Lawgpt 1.0： A Virtual Legal Assistant Based on GPT-3［EB/OL］. （2023-02-10）［2024-04-26］. https：//arxiv.org/abs/2302.05729.
［38］ YANG S H， ZHAO H J， ZHU S B， et al. Zhongjing： Enhancing the Chinese Medical Capabilities of Large Language Model Through Expert Feedback and Real-world Multi-Turn Dialogue［EB/OL］. （2023-08-07）［2024-04-26］. https：//arxiv.org/abs/2308.03549.
［39］ ZHANG X Y， YANG Q， XU D H. Xuanyuan 2.0： A large chinese financial chat model with hundreds of billions parameters［C］// Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. ACM， 2023：4435-4439.
［40］ YANG H R， ZHANG Y M， XU J Q， et al. Unveiling the generalization power of fine-tuned large language models［C］// Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. ACL， 2024：884-899.
［41］ LIU H， TAM D， MUQEETH M， et al. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning［J］. Advances in Neural Information Processing Systems， 2022，35：1950-1965.
［42］ LI X L， LIANG P. Prefix-tuning： Optimizing continuous prompts for generation［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. ACL， 2021：4582-4597.
［43］ HE R D， LIU L L， YE H， et al. On the effectiveness of adapter-based tuning for pretrained language model adaptation［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. ACL， 2021：2208-2222.
［44］ HU E J， WALLIS P， ALLEN-ZHU Z， et al. LoRA： Low-rank adaptation of large language models［C］// Proceedings of International Conference on Learning Representations. Springer， 2021：1-13.
［45］ DU Z X， QIAN Y J， LIU X， et al. GLM： General language model pretraining with autoregressive blank infilling［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. ACL， 2022：320-335.
［46］ TOUVRON H， LAVRIL T， IZACARD G， et al. Llama： Open and Efficient Foundation Language Models［EB/OL］. （2023-02-27）［2024-04-26］. https：//arxiv.org/abs/2302.
13971.
［47］ YANG A Y， XIAO B， WANG B N， et al. Baichuan 2： Open Large-scale Language Models［EB/OL］. （2023-09-18）［2024-04-26］. https：//arxiv.org/abs/2309.10305.
［48］ BAI J Z， BAI S， CHU Y F， et al. Qwen Technical Report［EB/OL］. （2023-09-28）［2024-04-26］. https：//arxiv.org/abs/2309.16609.
［49］ TEAM I L M. Internlm： A Multilingual Language Model with Progressively Enhanced Capabilities［EB/OL］. （2023-01-06）［2024-04-26］. https：//github.com/InternLM/InternLM.
［50］ THIRUNAVUKARASU A J， TING D S J， ELANGOVAN K， et al. Large language models in medicine［J］. Nature Medicine， 2023，29（8）：1930-1940.
［51］ CUI J X， LI Z J， YAN Y， et al. Chatlaw： Open-source Legal Large Language Model with Integrated External Knowledge Bases［EB/OL］. （2023-06-28）［2024-04-26］. https：
//arxiv.org/abs/2306.16092.
［52］ LEWIS P， PEREZ E， PIKTUS A， et al. Retrieval-augmented generation for knowledge-intensive NLP tasks［J］. Advances in Neural Information Processing Systems， 2020，33：9459-9474.
［53］ SIRIWARDHANA S， WEERASEKERA R， WEN E， et al. Improving the domain adaptation of retrieval augmented generation （RAG） models for open domain question answering［J］. Transactions of the Association for Computational Linguistics， 2023，11：1-17.
［54］ TOPSAKAL O， AKINCI T C. Creating large language model applications utilizing langchain： A primer on developing ll m APPs fast［C］// International Conference on Applied Engineering and Natural Sciences. IEEE， 2023：1050-1056.
［55］ LEETARU K， SCHRODT P A. GDELT： Global data on events， location， and tone， 1979-2012［J］. Citeseer， 2013，2（4）：1-49.
［56］ SHILLIDAY A， LAUTENSCHLAGER J. Data for a worldwide ICEWS and ongoing research［C］// Advances in Design for Cross-Cultural Activities. ACM， 2012：455.
［57］ RALEIGH C， LINKE R， HEGRE H， et al. Introducing ACLED： An armed conflict location and event dataset［J］. Journal of Peace Research， 2010，47（5）：651-660.
［58］ SUNDBERG R， MELANDER E. Introducing the UCDP georeferenced event dataset［J］. Journal of Peace Research， 2013，50（4）：523-532.
［59］ LAFREE G. The global terrorism database （GTD） accomplishments and challenges［J］. Perspectives on Terrorism， 2010，4（1）：24-46.
［60］ HOFFMANN J， BORGEAUD S， MENSCH A， et al. An empirical analysis of compute-optimal large language model training［J］. Advances in Neural Information Processing Systems， 2022，35：30016-30030.