可解释人工智能研究进展

doi:10.19678/j.issn.1000-3428.0069925

摘要/Abstract

摘要：

人工智能在诸多领域的应用取得了突破性的进展, 引起了全球各国对其研发的高度重视。然而, 人工智能的快速发展也带来了一系列的问题, 过度依赖和盲目信任人工智能模型可能导致严重的风险。因此, 可解释人工智能成为构建可信、透明的智能系统的关键要素, 其研发变得尤为迫切。为此, 本文综述可解释人工智能的国内外研究进展, 从多维度、多层次进行全面梳理与归纳。首先, 基于当前行业内的研究成果, 将可解释人工智能的关键技术细分为解释模型、解释方法、安全测试及实验验证4类, 旨在明确各领域的技术焦点与发展方向。然后, 探讨可解释人工智能在多个关键行业领域的具体应用实例, 包括但不限于教育、医疗、金融、自动驾驶及司法等, 展示其在提升决策透明度等方面的重要作用。最后, 深入剖析可解释人工智能当前面临的主要技术挑战, 并展望其未来的发展趋势, 尤其针对当前备受瞩目的大模型可解释性问题, 进行了专项调研与探讨分析。

关键词: 可解释性, 可信, 人工智能, 示范应用, 大模型

Abstract:

Artificial intelligence has made remarkable progress across many fields, encouraging countries to attach great importance to its research and development. However, the rapid development of artificial intelligence has also brought about a series of problems and threats, and overreliance on and blind trust in such models can lead to serious risks. Therefore, interpretable artificial intelligence has become a key element in building trusted and transparent intelligent systems, and its research and development requires immediate attention. This survey comprehensively summarizes the research progress on explainable artificial intelligence at home and abroad comprehensively from multiple dimensions and levels. Based on current research results in the industry, this survey subdivides the key technologies of explainable artificial intelligence into four categories: interpretation model, interpretation method, safety testing, and experimental verification, with the aim of clarifying the technical focus and development direction of each field. Furthermore, the survey explores specific application examples of explainable artificial intelligence across key industry sectors, including but not limited to education, healthcare, finance, autonomous driving, and justice, demonstrating the significant role it plays in enhancing decision-making transparency. Finally, this survey provides an in-depth analysis of the major technical challenges of interpretable artificial intelligence and presents future development trends, in addition to a special investigation and in-depth analysis of the interpretability of large models, which has attracted considerable attention recently.

Key words: interpretability, trustworthy, artificial intelligence, demonstration application, large model

廖勇, 韩小金, 刘金林, 汪浩. 可解释人工智能研究进展[J]. 计算机工程, 2026, 52(3): 41-61.

LIAO Yong, HAN Xiaojin, LIU Jinlin, WANG Hao. Research Progress of Interpretable Artificial Intelligence[J]. Computer Engineering, 2026, 52(3): 41-61.

https://www.ecice06.com/CN/Y2026/V52/I3/41

图/表 12

图1 可解释人工智能的关键技术分类

Fig.1 Classification of key technologies for interpretable artificial intelligence

图2 跨模态知识蒸馏示意图

Fig.2 Schematic diagram of cross-modal knowledge distillation

图3 可解释人工智能根据解释方法的分类

Fig.3 Classification of interpretable artificial intelligence by interpretation methods

图4 CAM总体网络结构

Fig.4 Structure of CAM overall network

图5 基于LDP的隐私保护模型结构

Fig.5 Structure of LDP-based privacy protection model

图6 基于服务的可信证据收集原子方法结构

Fig.6 Structure of the atomic method for service-based trusted evidence collection

图7 基于FRCNN的诊断方法示意图

Fig.7 Schematic diagram of FRCNN-based diagnosis method

参考文献 84

1	胡昌昊. 浅析人工智能的发展历程与未来趋势. 经济研究导刊, 2018 (31): 33-35, 196.
	HU C H . Analysis on the development course and future trend of artificial intelligence. Economic Research Guide, 2018 (31): 33-35, 196.
2	祝冰艳, 陈志华, 盛斌. 基于感知增强Swin Transformer的遥感图像检测. 计算机工程, 2024, 50 (1): 216- 223. doi: 10.19678/j.issn.1000-3428.0066941
	ZHU B Y , CHEN Z H , SHENG B . Remote sensing image detection based on perceptually enhanced Swin Transformer. Computer Engineering, 2024, 50 (1): 216- 223. doi: 10.19678/j.issn.1000-3428.0066941
3	姜百浩, 刘静, 仇大伟, 等. 深度学习在脊柱图像分割中的应用综述. 计算机工程, 2024, 50 (3): 1- 15. doi: 10.19678/j.issn.1000-3428.0067502
	JIANG B H , LIU J , QIU D W , et al. Review of deep learning applications in spinal image segmentation. Computer Engineering, 2024, 50 (3): 1- 15. doi: 10.19678/j.issn.1000-3428.0067502
4	杜晨阳, 张雪英, 黄丽霞, 等. 基于改进高效通道注意力机制的多特征语音情感识别. 计算机工程, 2025, 51 (4): 97- 106. doi: 10.19678/j.issn.1000-3428.0069185
	DU C Y , ZHANG X Y , HUANG L X , et al. Multi-feature speech emotion recognition based on improved efficient channel attention mechanism. Computer Engineering, 2025, 51 (4): 97- 106. doi: 10.19678/j.issn.1000-3428.0069185
5	刘帅威, 李智, 王国美, 等. 基于Transformer和GAN的对抗样本生成算法. 计算机工程, 2024, 50 (2): 180- 187. doi: 10.19678/j.issn.1000-3428.0067077
	LIU S W , LI Z , WANG G M , et al. Adversarial example generation algorithm based on Transformer and GAN. Computer Engineering, 2024, 50 (2): 180- 187. doi: 10.19678/j.issn.1000-3428.0067077
6	黄金贵, 刘朋, 唐文胜. MMD-YOLOv7:黑暗条件下车辆检测方法. 计算机工程, 2025, 51 (9): 340- 349. doi: 10.19678/j.issn.1000-3428.0069139
	HUANG J G , LIU P , TANG W S . MMD-YOLOv7: vehicle detection method under dark conditions. Computer Engineering, 2025, 51 (9): 340- 349. doi: 10.19678/j.issn.1000-3428.0069139
7	ZHANG T, QIN Y, LI Q. Trusted artificial intelligence: technique requirements and best practices[C]//Proceedings of the IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom). Washington D.C., USA: IEEE Press, 2021: 1458-1462.
8	闫宏秀. 可信任: 人工智能伦理未来图景的一种有效描绘. 理论探索, 2019 (4): 38-42, 63.
	YAN H X . Trustworthiness: an effective description of the future prospect of artificial intelligence ethics. Theoretical Exploration, 2019 (4): 38-42, 63.
9	车昊. 浅谈人工智能可解释性[EB/OL]. [2024-03-09]. https://mp.weixin.qq.com/s/dnEGiAbWWHbfLKsbAmojTA.
	CHE H. On the explainability of artificial intelligence[EB/OL]. [2024-03-09]. https://mp.weixin.qq.com/s/dnEGiAbWWHbfLKsbAmojTA. (in Chinese)
10	何华灿. 重新找回人工智能的可解释性. 智能系统学报, 2019, 14 (3): 393- 412.
	HE H C . Refining the interpretability of artificial intelligence. CAAI Transactions on Intelligent Systems, 2019, 14 (3): 393- 412.
11	国家自然科学基金委员会. 关于发布可解释、可通用的下一代人工智能方法重大研究计划2024年度项目指南的通告[EB/OL]. [2024-03-09]. https://mp.weixin.qq.com/s/FfBABf3DeWtCfWnIXUPH8Q.
	National Natural Science Foundation of China. Notice on the release of the 2024 annual project guidelines for the major research program on interpretable and general-purpose next generation artificial intelligence methods[EB/OL]. [2024-03-09]. https://mp.weixin.qq.com/s/FfBABf3DeWtCfWnIXUPH8Q. (in Chinese)
12	LIPTON Z C . The mythos of model interpretability. Queue, 2018, 16 (3): 31- 57. doi: 10.1145/3236386.3241340
13	王冬丽, 杨珊, 欧阳万里, 等. 人工智能可解释性: 发展与应用. 计算机科学, 2023, 50 (S1): 19- 25.
	WANG D L , YANG S , OUYANG W L , et al. Interpretability of artificial intelligence: development and application. Computer Science, 2023, 50 (S1): 19- 25.
14	赵延玉, 赵晓永, 王磊, 等. 可解释人工智能研究综述. 计算机工程与应用, 2023, 59 (14): 1- 14.
	ZHAO Y Y , ZHAO X Y , WANG L , et al. Review of explainable artificial intelligence. Computer Engineering and Applications, 2023, 59 (14): 1- 14.
15	WASHIZAKI H, YOSHIOKA N. AI security continuum: concept and challenges[C]//Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering-Software Engineering for AI. New York, USA: ACM Press, 2024: 1-8.
16	刘晗, 李凯旋, 陈仪香. 人工智能系统可信性度量评估研究综述. 软件学报, 2023, 34 (8): 3774- 3792.
	LIU H , LI K X , CHEN Y X . Survey on trustworthiness measurement for artificial intelligence systems. Journal of Software, 2023, 34 (8): 3774- 3792.
17	闵继源, 鲁统宇, 任婷婷, 等. 基于规则集成的可解释机器学习算法及应用. 计算机科学与探索, 2024, 18 (6): 1476- 1490.
	MIN J Y , LU T Y , REN T T , et al. Interpretable machine learning algorithm based on rules ensemble and its application. Journal of Frontiers of Computer Science and Technology, 2024, 18 (6): 1476- 1490.
18	周志杰, 曹友, 胡昌华, 等. 基于规则的建模方法的可解释性及其发展. 自动化学报, 2021, 47 (6): 1201- 1216.
	ZHOU Z J , CAO Y , HU C H , et al. The interpretability of rule-based modeling approach and its development. Acta Automatica Sinica, 2021, 47 (6): 1201- 1216.
19	汪祖民, 王恺锋, 李艳志, 等. 基于LightGBM和SHAP的云南省森林火灾预测研究. 消防科学与技术, 2023, 42 (11): 1567- 1571.
	WANG Z M , WANG K F , LI Y Z , et al. Research on forest fire prediction in Yunnan province based on LightGBM and SHAP. Fire Science and Technology, 2023, 42 (11): 1567- 1571.
20	郑可欣, 江雨欣, 毕可鑫, 等. 用于蒸汽裂解产物成分预测的集成迁移学习框架. 化工进展, 2024, 43 (5): 2880- 2889.
	ZHENG K X , JIANG Y X , BI K X , et al. Ensemble transfer learning framework for outflow compositions prediction in steam cracking process. Chemical Industry and Engineering Progress, 2024, 43 (5): 2880- 2889.
21	ZHAO L, PENG X, CHEN Y X, et al. Knowledge as priors: cross-modal knowledge generalization for datasets without superior knowledge[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 6527-6536.
22	SETZU M , GUIDOTTI R , MONREALE A , et al. GLocalX — from local to global explanations of black box AI models. Artificial Intelligence, 2021, 294, 103457. doi: 10.1016/j.artint.2021.103457
23	秦利娟, 冯乃勤. 基于深度学习反向传播的稀疏数据特征提取. 计算机仿真, 2022, 39 (5): 333-336, 469.
	QIN L J , FENG N Q . Sparse data feature extraction of sparse data based on deep learning back propagation. Computer Simulation, 2022, 39 (5): 333-336, 469.
24	LUNDBERG S M , ERION G , CHEN H , et al. From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2020, 2, 56- 67. doi: 10.1038/s42256-019-0138-9
25	JOSHI R, KARNAVAT R, JIRAPURE K, et al. Evaluation of deep learning models for hostility detection in Hindi text[C]//Proceedings of the 6th International Conference for Convergence in Technology (I2CT). Washington D.C., USA: IEEE Press, 2021: 1-5.
26	李永飞, 李铭洋, 常鑫, 等. 基于可解释性深度学习的物联网水质监测数据异常检测. 计算机工程, 2024, 50 (6): 179- 187. doi: 10.19678/j.issn.1000-3428.0067570
	LI Y F , LI M Y , CHANG X , et al. Anomaly detection of IoT water quality monitoring data based on explainable deep learning. Computer Engineering, 2024, 50 (6): 179- 187. doi: 10.19678/j.issn.1000-3428.0067570
27	YEGANEJOU M , DICK S , MILLER J . Interpretable deep convolutional fuzzy classifier. IEEE Transactions on Fuzzy Systems, 2020, 28 (7): 1407- 1419.
28	姚远, 李艳, 张朝阳, 等. 可解释性收益率预测模型. 系统工程, 2024, 42 (1): 130- 138.
	YAO Y , LI Y , ZHANG Z Y , et al. Interpretable rate of return prediction model. Systems Engineering, 2024, 42 (1): 130- 138.
29	MOLNAR C , CASALICCHIO G , BISCHL B . Interpretable machine learning—a brief history, state-of-the-art and challenges. Berlin, Germany: Springer, 2020.
30	向许, 于洪, 张晓霞, 等. IsomapVSG-LIME: 一种新的模型无关解释方法. 智能系统学报, 2023, 18 (4): 841- 848.
	XIANG X , YU H , ZHANG X X , et al. IsomapVSG-LIME: a novel local interpretable model-agnostic explanations. CAAI Transactions on Intelligent Systems, 2023, 18 (4): 841- 848.
31	张宇, 梁凤梅, 刘建霞. 融合类激活映射和视野注意力的皮肤病变分割. 计算机工程与应用, 2023, 59 (21): 187- 194.
	ZHANG Y , LIANG F M , LIU J X . Skin lesion segmentation based on classification activation mapping and visual field attention. Computer Engineering and Applications, 2023, 59 (21): 187- 194.
32	周登极, 刘巧珍, 岳梦云, 等. 基于可解释模型的火箭推力故障辨识与轨迹预测方法. 电子测量与仪器学报, 2023, 37 (11): 72- 80.
	ZHOU D J , LIU Q Z , YUE M Y , et al. Method for thrust fault identification and trajectory prediction of launch vehicle based on interpretable machine learning model. Journal of Electronic Measurement and Instrumentation, 2023, 37 (11): 72- 80.
33	BACH S , BINDER A , MONTAVON G , et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One, 2015, 10 (7): e0130140. doi: 10.1371/journal.pone.0130140
34	SHRIKUMAR A, GREENSIDE P, KUNDAJE A. Learning important features through propagating activation differences[C]//Proceedings of International Conference on Machine Learning. Washington D.C., USA: IEEE Press, 2017: 3145-3153.
35	FAN F L , XIONG J J , LI M Z , et al. On interpretability of artificial neural networks: a survey. IEEE Transactions on Radiation and Plasma Medical Sciences, 2021, 5 (6): 741- 760. doi: 10.1109/TRPMS.2021.3066428
36	辛梓铭, 王芳. 基于改进朴素贝叶斯算法的文本分类研究. 燕山大学学报, 2023, 47 (1): 82- 88.
	XIN Z M , WANG F . Research on text classification based on improved naive Bayes algorithm. Journal of Yanshan University, 2023, 47 (1): 82- 88.
37	郑力嘉, 宋冰. 决策树分类算法的预剪枝与优化. 自动化仪表, 2023, 44 (5): 56- 62.
	ZHENG L J , SONG B . Pre-pruning and optimization of decision tree classification algorithm. Process Automation Instrumentation, 2023, 44 (5): 56- 62.
38	鞠天杰, 刘功申, 张倬胜, 等. 自然语言处理中的探针可解释方法综述. 计算机学报, 2024, 47 (4): 733- 758.
	JU T J , LIU G S , ZHANG Z S , et al. A review of probe interpretable methods in natural language processing. Chinese Journal of Computers, 2024, 47 (4): 733- 758.
39	上海丰蕾信息科技有限公司. 机器学习模型的全局解释优化方法、系统、介质及设备: CN202311630644.4[P]. 2024-03-26.
	Shanghai Fenglei Information Technology Co., Ltd. Global interpretation optimization methods, systems, media, and devices for machine learning models: CN202311630644.4[P]. 2024-03-26. (in Chinese)
40	LUSS R, CHEN P Y, DHURANDHAR A, et al. Leveraging latent features for local explanations[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: ACM Press, 2021: 2974-2983.
41	HYNES N, SCULLEY D, TERRY M. The Data Linter: lightweight automated sanity checking for ML data sets[C]//Proceedings of NIPS MLSys Workshop. Cambridge, USA: MIT Press, 2017: 1-8.
42	王亚伦, 周涛, 陈中, 等. 基于堆叠式降噪自动编码器和深度神经网络的风电调频逐步惯性智能控制. 上海交通大学学报, 2023, 57 (11): 1477- 1491.
	WANG Y L , ZHOU T , CHEN Z , et al. Stepwise inertial intelligent control of wind power for frequency regulation based on stacked denoising autoencoder and deep neural network. Journal of Shanghai Jiao Tong University, 2023, 57 (11): 1477- 1491.
43	HASSAN M M, AFZAL W, BLOM M, et al. Testability and software robustness: a systematic literature review[C]//Proceedings of the 41st Euromicro Conference on Software Engineering and Advanced Applications. Washington D.C., USA: IEEE Press, 2015: 341-348.
44	孙家泽, 唐彦梅, 王曙燕. 利用GAN和特征金字塔的模型鲁棒性优化方法. 计算机科学与探索, 2023, 17 (5): 1139- 1146.
	SUN J Z , TANG Y M , WANG S Y . Model robustness optimization method using GAN and feature pyramid. Journal of Frontiers of Computer Science and Technology, 2023, 17 (5): 1139- 1146.
45	赵子天, 詹文翰, 段翰聪, 等. 基于SVD的深度学习模型对抗鲁棒性研究. 计算机科学, 2023, 50 (10): 362- 368.
	ZHAO Z T , ZHAN W H , DUAN H C , et al. Study on adversarial robustness of deep learning models based on SVD. Computer Science, 2023, 50 (10): 362- 368.
46	ANGELL R, JOHNSON B, BRUN Y, et al. Themis: automatically testing software for discrimination[C]//Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York, USA: ACM Press, 2018: 871-875.
47	BLACK E, YEOM S, FREDRIKSON M. FlipTest: fairness testing via optimal transport[C]//Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. New York, USA: ACM Press, 2020: 111-121.
48	GUO Q Y, CHEN S, XIE X F, et al. An empirical study towards characterizing deep learning development and deployment across different frameworks and platforms[C]// Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE). Washington D.C., USA: IEEE Press, 2019: 810-822.
49	LIU L, WU Y Z, WEI W Q, et al. Benchmarking deep learning frameworks: design considerations, metrics and beyond[C]//Proceedings of the IEEE 38th International Conference on Distributed Computing Systems (ICDCS). Washington D.C., USA: IEEE Press, 2018: 1258-1269.
50	CHEN Z P, YAO H H, LOU Y L, et al. An empirical study on deployment faults of deep learning based mobile applications[C]//Proceedings of the IEEE/ACM 43rd International Conference on Software Engineering (ICSE). Washington D.C., USA: IEEE Press, 2021: 674-685.
51	侯慧莹, 廉欢欢, 赵运磊. 面向自动驾驶的高效可追踪的车联网匿名通信方案. 计算机研究与发展, 2022, 59 (4): 894- 906.
	HOU H Y , LIAN H H , ZHAO Y L . An efficient and traceable anonymous VANET communication scheme for autonomous driving. Journal of Computer Research and Development, 2022, 59 (4): 894- 906.
52	钱文君, 沈晴霓, 吴鹏飞, 等. 大数据计算环境下的隐私保护技术研究进展. 计算机学报, 2022, 45 (4): 669- 701.
	QIAN W J , SHEN Q N , WU P F , et al. Research progress on privacy-preserving techniques in big data computing environment. Chinese Journal of Computers, 2022, 45 (4): 669- 701.
53	李可佳, 胡学先, 陈越, 等. 基于主成分分析和函数机制的差分隐私线性回归算法. 计算机科学, 2023, 50 (8): 342- 351.
	LI K J , HU X X , CHEN Y , et al. Differential privacy linear regression algorithm based on principal component analysis and functional mechanism. Computer Science, 2023, 50 (8): 342- 351.
54	GE L, GAO J, LI X Y, et al. Multi-source deep learning for information trustworthiness estimation[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM Press, 2013: 755-774.
55	TABIBIAN B, VALERA I, FARAJTABAR M, et al. Distilling information reliability and source trustworthiness from digital traces[C]//Proceedings of the 26th International Conference on World Wide Web. Perth, Australia: International World Wide Web Conferences Steering Committee, 2017: 847-855.
56	FOGLIARONI P , D'ANTONIO F , CLEMENTINI E . Data trustworthiness and user reputation as indicators of VGI quality. Geo-spatial Information Science, 2018, 21 (3): 213- 233. doi: 10.1080/10095020.2018.1496556
57	ARDAGNA C A, ASAL R, DAMIANI E, et al. Trustworthy IoT: an evidence collection approach based on smart contracts[C]// Proceedings of the IEEE International Conference on Services Computing. Washington D.C., USA: IEEE Press, 2019: 46-50.
58	DISTEFANO S , DI GIACOMO A , MAZZARA M . Trustworthiness for transportation ecosystems: the blockchain vehicle information system. IEEE Transactions on Intelligent Transportation Systems, 2021, 22 (4): 2013- 2022. doi: 10.1109/TITS.2021.3054996
59	BAU D, ZHOU B L, KHOSLA A, et al. Network dissection: quantifying interpretability of deep visual representations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2017: 3319-3327.
60	SLACK D, FRIEDLER S A, SCHEIDEGGER C, et al. Assessing the local interpretability of machine learning models[EB/OL]. [2024-03-26]. https://arx-iv.org/abs/1902.03501.
61	ROSENFELD A. Better metrics for evaluating explainable artificial intelligence[C]//Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems. London, UK: International Foundation for Autonomous Agents and Multiagent Systems, 2021: 45-50.
62	SONG L W, MITAL P. Systematic evaluation of privacy risks of machine learning models[C]//Proceedings of the 30th USENIX Security Symposium. [S. l.]: USENIX Association, 2021: 2615-2632.
63	MA R , LI J Q , XING B H , et al. A novel similar player clustering method with privacy preservation for sport performance evaluation in cloud. IEEE Access, 2021, 9, 37255- 37261. doi: 10.1109/ACCESS.2021.3062735
64	周志华. 机器学习. 北京: 清华大学出版社, 2016.
	ZHOU Z H . Machine learning. Beijing: Tsinghua University Press, 2016.
65	JHA S, RAJ S, FERNANDES S L, et al. Attribution-based confidence metric for deep neural networks[C]//Proceedings of the 33rd Interantional Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2019: 11837-11848.
66	YANGZEN T H, HONG C B, MOHAN P M, et al. ABC-verify: AI-blockchain integrated framework for tweet misinformation detection[C]//Proceedings of the IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI). Washington D.C., USA: IEEE Press, 2021: 1-8.
67	刘桐, 顾小清. 走向可解释性: 打开教育中人工智能的"黑盒". 中国电化教育, 2022 (5): 82- 90.
	LIU T , GU X Q . Opening the "black box": exploring the interpretability of artificial intelligence in education. China Educational Technology, 2022 (5): 82- 90.
68	江波, 丁莹雯, 魏雨昂. 教育数字化转型的核心技术引擎: 可信教育人工智能. 华东师范大学学报(教育科学版), 2023, 41 (3): 52- 61.
	JIANG B , DING Y W , WEI Y A . The core technology engine of digital transformation in education: trustworthy education artificial intelligence. Journal of East China Normal University (Educational Sciences), 2023, 41 (3): 52- 61.
69	王萍, 田小勇, 孙侨羽. 可解释教育人工智能研究: 系统框架、应用价值与案例分析. 远程教育杂志, 2021, 39 (6): 20- 29.
	WANG P , TIAN X Y , SUN Q Y . Research on explainable artificial intelligence for education: system framework, application value and case analysis. Journal of Distance Education, 2021, 39 (6): 20- 29.
70	黄荣怀. 教育领域中的可信人工智能: 机遇与挑战. 华中师范大学学报(人文社会科学版), 2023, 62 (5): 10- 15.
	HUANG R H . Trusted artificial intelligence in education: opportunities and challenges. Journal of Huazhong Normal University (Humanities and Social Sciences), 2023, 62 (5): 10- 15.
71	沈苑, 胡梦圆, 范逸洲, 等. 可信赖人工智能教育应用的建设路径与现实启示——以英国典型举措为例. 现代远程教育研究, 2023, 35 (4): 65- 74.
	SHEN Y , HU M Y , FAN Y Z , et al. Path and enlightenment of trustworthy artificial intelligence in education: a case study of typical initiatives in the United Kingdom. Modern Distance Education Research, 2023, 35 (4): 65- 74.
72	郝烨, 王浩. 人工智能医疗器械可信赖性研究. 中国医疗设备, 2023, 38 (3): 56- 60.
	HAO Y , WANG H . Research on trustworthiness of artificial intelligence-based medical devices. China Medical Devices, 2023, 38 (3): 56- 60.
73	井杰, 王蓓蕾, 刘善荣. 可解释人工智能在疾病诊疗中的应用. 检验医学, 2021, 36 (9): 976- 980.
	JING J , WANG B L , LIU S R . Explainable artificial intelligence in disease diagnosis and treatment. Laboratory Medicine, 2021, 36 (9): 976- 980.
74	VOLKOV E N, AVERKIN A N. Gradient-based explainable artificial intelligence methods for eye disease classification[C]//Proceedings of the IV International Conference on Neural Networks and Neurotechnologies (NeuroNT). Washington D.C., USA: IEEE Press, 2023: 6-9.
75	KARIM M R, COCHEZ M, BEYAN O, et al. OncoNetExplainer: explainable predictions of cancer types based on gene expression data[C]//Proceedings of the IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). Washington D.C., USA: IEEE Press, 2019: 415-422.
76	KARIM M R , JIAO J , DÖHMEN T , et al. DeepKneeExplainer: explainable knee osteoarthritis diagnosis from radiographs and magnetic resonance imaging. IEEE Access, 2021, 9, 39757- 39780. doi: 10.1109/ACCESS.2021.3062493
77	陈骞. 经济合作与发展组织促进可信人工智能发展. 上海信息化, 2023 (5): 50- 52.
	CHEN Q . Organization for economic cooperation and development promotes the development of trusted artificial intelligence. Shanghai Informatization, 2023 (5): 50- 52.
78	丁晓蔚, 苏新宁. 基于区块链可信大数据人工智能的金融安全情报分析. 情报学报, 2019, 38 (12): 1297- 1309.
	DING X W , SU X N . Financial security intelligence analysis based on blockchain driven trustable big data and AI. Journal of the China Society for Scientific and Technical Information, 2019, 38 (12): 1297- 1309.
79	郭炜炜, 王琦. 人-无人车交互中的可解释性交互研究. 包装工程, 2020, 41 (18): 22- 28.
	GUO W W , WANG Q . Explainable interaction in human-autonomous vehicle interaction. Packaging Engineering, 2020, 41 (18): 22- 28.
80	刘艳红. 人工智能的可解释性与AI的法律责任问题研究. 法制与社会发展, 2022, 28 (1): 78- 91.
	LIU Y H . On the explainability and legal liability of artificial intelligence. Law and Social Development, 2022, 28 (1): 78- 91.
81	邱遥堃. 机遇与风险: 文生视频大模型将如何影响智慧法院建设升级迭代. 中国应用法学, 2024 (2): 89- 98.
	QIU Y K . Opportunities and the risks: how the video generation models will affect the upgrading and iteration of the construction of smart courts. China Journal of Applied Jurisprudence, 2024 (2): 89- 98.
82	曹建峰. 迈向可信AI: ChatGPT类生成式人工智能的治理挑战及应对. 上海政法学院学报(法治论丛), 2023, 38 (4): 28- 42.
	CAO J F . Towards trustworthy AI: the governance challenges and responses for generative AI like ChatGPT. Journal of Shanghai University of Political Science and Law (the Rule of Law Forum), 2023, 38 (4): 28- 42.
83	胡晓萌, 陈力源, 刘正源. 大语言模型的信任建构. 中州学刊, 2024 (5): 171- 176.
	HU X M , CHEN L Y , LIU Z Y . The trust construction of large language models. Academic Journal of Zhongzhou, 2024 (5): 171- 176.
84	ZHAO H Y , CHEN H J , YANG F , et al. Explainability for large language models: a survey. ACM Transactions on Intelligent Systems and Technology, 2024, 15 (2): 1- 38.

[1]	王利民, 朱光辉, 吴涛. 大模型技术演进：世界模型让人工智能从感知走向决策(特邀)[J]. 计算机工程, 2026, 52(2): 1-6.
[2]	刘娟, 胡雪莲, 朱美蓉, 冯梦兰, 温素月. AIGC支持下教学动画中虚拟教师的应用效果研究[J]. 计算机工程, 2025, 51(8): 341-353.
[3]	张玉博, 杨帆, 郭亚, 杨文慧. 基于视觉大模型的垃圾分类轻量化算法研究[J]. 计算机工程, 2025, 51(7): 140-151.
[4]	王浩, 高锦涛, 王杰. 基于机器学习的数据库多表连接顺序选择研究综述[J]. 计算机工程, 2025, 51(7): 31-46.
[5]	郭佩林, 张德, 王怀秀. 基于特征可视化探究跳跃连接结构对深度神经网络特征提取的影响[J]. 计算机工程, 2025, 51(4): 149-157.
[6]	齐凤林, 沈佳杰, 王茂异, 张凯, 王新. 人工智能在高校信息化中的应用研究综述[J]. 计算机工程, 2025, 51(4): 1-14.
[7]	刘云翔, 梁智超. 一种高效的连续时序图注意力网络的交通预测模型[J]. 计算机工程, 2025, 51(4): 350-359.
[8]	张树华, 王继业, 赵传奇, 陈宏铭, 郭咏雯. 面向输电线路边缘智能的硬件加速设计[J]. 计算机工程, 2025, 51(2): 213-222.
[9]	廖牛语, 田沄, 李岩松, 薛海峰, 杜长坤, 张国华. 大模型工具学习: 方法、作用与机制[J]. 计算机工程, 2025, 51(12): 1-17.
[10]	李瑞, 文敏华, 范寅, 徐冬阳, 张战炳, 林新华. 基于拒绝采样的多起始点全局优化算法[J]. 计算机工程, 2025, 51(10): 150-159.
[11]	李亚康, 李健芳, 胡鹏, 陈娟, 王声翔, 齐法制, 陈刚. 人工智能在中子散射实验全生命周期中的应用综述[J]. 计算机工程, 2025, 51(10): 53-70.
[12]	胡升龙, 陈彬, 张开华, 宋慧慧. 场景结构知识增强的协同显著性目标检测[J]. 计算机工程, 2025, 51(1): 31-41.
[13]	郑清安, 董建成, 陈亮, 阮英清, 李锦松, 许林彬. 分布式可信数据管理与隐私保护技术研究[J]. 计算机工程, 2024, 50(7): 174-186.
[14]	赵云涛, 肖俊杰, 李维刚, 熊雅婷. 基于改进PPYOLOE-R的信息码矫正研究[J]. 计算机工程, 2024, 50(6): 358-366.
[15]	李敬灿, 肖萃林, 覃晓婷, 谢夏. 基于大语言模型与语义增强的文本关系抽取算法[J]. 计算机工程, 2024, 50(4): 87-94.

选择文件类型/文献管理软件名称

选择包含的内容