Review of False Information Detection Frameworks Based on Large Language Models

doi:10.3778/j.issn.1673-9418.2411001

Abstract

Abstract: Globally, the spread of false information on the Internet, especially on social media, has become an urgent issue to be addressed. With the rise of artificial intelligence technology, the application research of large language models in false information detection has become a hot topic. However, in China, related research in this field is relatively scarce and has not yet formed a complete system. To systematically review the current research status and development trends, this paper provides a comprehensive summary of the application of large language models in false information detection. This paper focuses on the false information detection framework based on large language models and deeply explores the innovative applications of large language models in data generation, data augmentation, information extraction, integration with external knowledge and tools, model improvement, final fusion decision-making, explanation and feedback generation during the false information detection process. It outlines the definition of false information and the background of its spread, elaborates on the core detection process in the framework, sorts out the innovation points in each link of the false information detection framework, summarizes the “internal” and “external” detection processes, and expounds on the model improvements such as retrieval enhancement, prompt engineering, fine-tuning, and final decision-making involved in the detection process. Finally, it analyzes the challenges faced by false information detection based on large language models at present and looks forward to future research directions, with the aim of providing references and inspirations for the development of false information detection based on large language models.

Key words: large language models, false information detection, data augmentation, key information extraction

摘要： 在全球范围内，虚假信息于互联网尤其是社交媒体中的传播，已成为亟待解决的重要议题。随着人工智能技术的兴起，虚假信息检测中大语言模型的应用研究已然成为热点。但在国内，该领域相关研究较为匮乏，尚未形成完整体系。为系统梳理其研究现状及发展脉络，对大语言模型赋能虚假信息检测的研究进行了全面总结。聚焦于基于大语言模型的虚假信息检测框架，深入探讨了大语言模型在虚假信息检测过程中数据生成、数据增强、信息抽取、结合外部知识和工具、模型改进、最终融合决策、解释与反馈生成等方面的创新应用。概述了虚假信息的定义及其传播的背景，详细剖析了框架中的核心检测过程，梳理了虚假信息检测框架中各环节的创新点，对“内部”与“外部”的检测流程进行概述，并阐述了检测过程中涉及的检索增强、提示工程、微调等模型改进与最终决策。最后，分析了当前基于大语言模型的虚假信息检测面临的挑战，并对未来的研究方向进行了展望，以期为基于大语言模型的虚假信息检测领域的发展提供借鉴与启示。

关键词: 大语言模型, 虚假信息检测, 数据增强, 关键信息抽取

ZHANG Xin, SUN Jingchao. Review of False Information Detection Frameworks Based on Large Language Models[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(6): 1414-1436.

张欣, 孙靖超. 基于大语言模型的虚假信息检测框架综述[J]. 计算机科学与探索, 2025, 19(6): 1414-1436.

References

[1] DON F. What is disinformation?[J]. Library Trends, 2015, 63(3): 401-426.
[2] GUO B, DING Y S, YAO L N, et al. The future of false information detection on social media[J]. ACM Computing Surveys, 2021, 53(4): 1-36.
[3] HU Y J, JU X Y, YE Z S, et al. Early rumor detection based on data augmentation and pre-training transformer[C]//Proceedings of the 2022 IEEE 12th Annual Computing and Communication Workshop and Conference. Piscataway: IEEE, 2022: 152-158.
[4] ZHOU X Y, JAIN A, PHOHA V V, et al. Fake news early detection: an interdisciplinary study[EB/OL]. [2024-08-10]. https://arxiv.org/abs/1904.11679.
[5] HABIB A, ASGHAR M Z, KHAN A, et al. False information detection in online content and its role in decision making: a systematic literature review[J]. Social Network Analysis and Mining, 2019, 9(1): 50.
[6] CAPUANO N, FENZA G, LOIA V, et al. Content-based fake news detection with machine and deep learning: a systematic review[J]. Neurocomputing, 2023, 530: 91-103.
[7] MRIDHA M F, KEYA A J, HAMID M A, et al. A comprehensive review on fake news detection with deep learning[J]. IEEE Access, 2021, 9: 156151-156170.
[8] LUO Z R, LI Q Q, ZHENG J. Deep feature fusion for rumor detection on twitter[J]. IEEE Access, 2021, 9: 126065-126074.
[9] 朱奕, 王根生, 金文文, 等. 基于文本语义增强和评论立场加权的网络谣言检测[J]. 计算机科学与探索, 2024, 18(12): 3311-3323.
ZHU Y, WANG G S, JIN W W, et al. Network rumor detection based on enhanced textual semantics and weighted comment stance[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(12): 3311-3323.
[10] CHEN C Y, SHU K. Combating misinformation in the age of LLMs: opportunities and challenges[J]. AI Magazine, 2024, 45(3): 354-368.
[11] LIU Y, ZHU J J, LIU X K, et al. Detect, investigate, judge and determine: a knowledge-guided framework for few-shot fake news detection[EB/OL]. [2024-08-10]. https://arxiv.org/ abs/2407.08952.
[12] YANG Y Z, ZHOU Y M, YING Q C, et al. Fact-checking based fake news detection: a review[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2401.01717.
[13] ANGGRAININGSIH R, HASSAN G M, DATTA A. Evaluating BERT-based pre-training language models for detecting misinformation[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2203.07731.
[14] SLIMI H, BOUNHAS I, SLIMANI Y. Adapting pre-trained language models to rumor detection on Twitter[J]. Journal of Universal Computer Science, 2021, 27(10): 1128-1148.
[15] LUND B D, WANG T. Chatting about ChatGPT: how may AI and GPT impact academia and libraries?[J]. Library Hi Tech News, 2023, 40(3): 26-29.
[16] TOUVRON H, LAVRIL T, IZACARD G, et al. LLaMA: open and efficient foundation language models[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2302.13971.
[17] CHOWDHERY A, NARANG S R, DEVLIN J, et al. PaLM: scaling language modeling with pathways[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2204.02311.
[18] QI P, YAN Z H, HSU W, et al. SNIFFER: multimodal large language model for explainable out-of-context misinformation detection[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 13052-13062.
[19] LIU Z W, YANG K L, XIE Q Q, et al. RAEmoLLM: retrieval augmented LLMs for cross-domain misinformation detection using in-context learning based on emotional information[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2406. 11093.
[20] LI X Y, ZHANG Y F, MALTHOUSE E C. Large language model agent for fake news detection[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2405.01593.
[21] KOKA S, VUONG A, KATARIA A. Evaluating the efficacy of large language models in detecting fake news: a comparative analysis[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2406.06584.
[22] BOISSONNEAULT D, HENSEN E. Fake news detection with large language models on the LIAR dataset[Z]. 2024.
[23] RONY M M U, HAQUE M M, ALI M, et al. Exploring the potential of the large language models (LLMs) in identifying misleading news headlines[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2405.03153.
[24] TAN X, ZOU B W, AW A T. Evidence-based interpretable open-domain fact-checking with large language models[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2312.05834.
[25] WANG H R, SHU K. Explainable claim verification via knowledge-grounded reasoning with large language models[C]//Findings of the Association for Computational Linguistics: EMNLP 2023. Stroudsburg: ACL, 2023: 6288-6304.
[26] LUCAS J, UCHENDU A, YAMASHITA M, et al. Fighting fire with fire: the dual role of LLMs in crafting and detecting elusive disinformation[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2310.15515.
[27] PAVLYSHENKO B M. Analysis of disinformation and fake news detection using fine-tuned large language model[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2309.04704.
[28] FREEDMAN G, DEJL A, GORUR D, et al. Argumentative large language models for explainable and contestable decision-making[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2405.02079.
[29] PENDYALA V S, HALL C E. Explaining misinformation detection using large language models[J]. Electronics, 2024, 13(9): 1673.
[30] LAI J Q, YANG X R, LUO W Y, et al. RumorLLM: a rumor large language model-based fake-news-detection data-augmentation approach[J]. Applied Sciences, 2024, 14(8): 3532.
[31] ZHANG L, LIU J W. Study on the effectiveness of multilingual models in fake news classification[C]//Proceedings of the 2024 IEEE 7th Information Technology, Networking, Electronic and Automation Control Conference. Piscataway: IEEE, 2024: 1516-1522.
[32] 陈静, 周刚, 李顺航, 等. 社交媒体虚假信息检测研究综述[J]. 计算机科学, 2024, 51(11): 1-14.
CHEN J, ZHOU G, LI S H, et al. Review of fake news detection on social media[J]. Computer Science, 2024, 51(11): 1-14.
[33] LIU Y, ITER D, XU Y C, et al. G-Eval: NLG evaluation using GPT-4 with better human alignment[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2303.16634.
[34] KIM K, LEE S Y, HUANG K H, et al. Can LLMs produce faithful explanations for fact-checking?towards faithful explainable fact-checking via multi-agent debate[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2402.07401.
[35] SZCZEPA?SKI M, PAWLICKI M, KOZIK R, et al. New explainability method for BERT-based model in fake news detection[J]. Scientific Reports, 2021, 11(1): 23705.
[36] LI Q Z, ZHANG Q, SI L, et al. Rumor detection on social media: datasets, methods and opportunities[C]//Proceedings of the 2nd Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda. Stroudsburg: ACL, 2019: 66-75.
[37] PAN L M, WU X B, LU X Y, et al. Fact-checking complex claims with program-guided reasoning[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2023: 6981-7004.
[38] LI M R, PENG B L, GALLEY M, et al. Self-checker: plug-and-play modules for fact-checking with large language models[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2305.14623.
[39] GUAN J, DODGE J, WADDEN D, et al. Language models hallucinate, but may excel at fact verification[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2310.14564.
[40] WAN H R, FENG S B, TAN Z X, et al. DELL: generating reactions and explanations for LLM-based misinformation detection[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2402.10426.
[41] YANG C, ZHANG P, QIAO W B, et al. Rumor detection on social media with crowd intelligence and ChatGPT-assisted networks[C]//Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2023: 5705-5717.
[42] HU B Z, SHENG Q, CAO J, et al. Bad actor, good advisor: exploring the role of large language models in fake news detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(20): 22105-22113.
[43] LIU H, WANG W Y, LI H R, et al. TELLER: a trustworthy framework for explainable, generalizable and controllable fake news detection[EB/OL]. [2024-08-10]. https://arxiv.org/ abs/2402.07776.
[44] PARK S, HAN S, CHA M. Adversarial style augmentation via large language model for robust fake news detection[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2406.11260.
[45] NAN Q, SHENG Q, CAO J, et al. Let silence speak: enhancing fake news detection with generated comments from large language models[C]//Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. New York: ACM, 2024: 1732-1742.
[46] CHEUNG T H, LAM K M. FactLLaMA: optimizing instruction-following language models with external knowledge for automated fact-checking[C]//Proceedings of the 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference. Piscataway: IEEE, 2023: 846-853.
[47] HUANG K H, MCKEOWN K, NAKOV P, et al. Faking fake news for real fake news detection: propaganda-loaded training data generation[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2023: 14571-14589.
[48] 柯婧, 谢哲勇, 徐童, 等. 基于大语言模型隐含语义增强的细粒度虚假新闻检测方法[J]. 计算机研究与发展, 2024, 61(5): 1250-1260.
KE J, XIE Z Y, XU T, et al. An implicit semantic enhanced fine-grained fake news detection method based on large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1250-1260.
[49] AZRI A, FAVRE C, HARBI N, et al. DAT@Z21: a comprehensive multimodal dataset for rumor classification in Micro-blogs[C]//Proceedings of the 25th International Conference on Big Data Analytics and Knowledge Discovery. Cham: Springer, 2023: 161-175.
[50] HE Y, WU Y H, ZHANG J R, et al. LTCR: long temporal characteristic reconstruction for segmentation in contrastive learning[C]//Proceedings of the Research Track-European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer, 2024: 355-371.
[51] SUNDRIYAL M, CHAKRABORTY T, NAKOV P. From chaos to clarity: claim normalization to empower fact-checking [EB/OL]. [2024-08-10]. https://arxiv.org/abs/2310.14338.
[52] ZUBIAGA A, LIAKATA M, PROCTER R, et al. Analysing how people orient to and spread rumours in social media by looking at conversational threads[J]. PLoS One, 2016, 11(3): e0150989.
[53] KOCHKINA E, LIAKATA M, ZUBIAGA A. All-in-one: multi-task learning for rumour verification[EB/OL]. [2024-08-10]. https://arxiv.org/abs/1806.03713.
[54] MA J, GAO W, WONG K F. Detect rumors in microblog posts using propagation structure via kernel learning[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2017: 708-717.
[55] SINGER-VINE C S, STRAPAGIEL L, SHABAN H, et al. Hyperpartisan facebook pages are publishing false and misleading information at an alarming rate[EB/OL]. (2016-10-20)[2024-08-10]. https://www.buzzfeednews.com/article/craigsilverman/partisan-fb-pages-analysis.
[56] GORRELL G, KOCHKINA E, LIAKATA M, et al. SemEval-2019 task 7: rumoureval, determining rumour veracity and support for rumours[C]//Proceedings of the 13th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2019: 845-854.
[57] SHU K, MAHUDESWARAN D, WANG S H, et al. FakeNewsNet: a data repository with news content, social context, and spatiotemporal information for studying fake news on social media[J]. Big Data, 2020, 8(3): 171-188.
[58] THORNE J, VLACHOS A, CHRISTODOULOPOULOS C, et al. FEVER: a large-scale dataset for fact extraction and verification[EB/OL]. [2024-08-10]. https://arxiv.org/abs/1803. 05355.
[59] WANG L Z, MA Y M, GAO R F, et al. MegaFake: a theory-driven dataset of fake news generated by large language models[EB/OL]. [2024-08-25]. https://arxiv.org/abs/2408. 11871.
[60] HUANG Y, SUN L C. FakeGPT: fake news generation, explanation and detection of large language models[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2310.05046.
[61] LI Z Z, ZHANG H P, ZHANG J W. A revisit of fake news dataset with augmented fact-checking by ChatGPT[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2312.11870.
[62] CAO Y P, NAIR A M, EYIMIFE E, et al. Can large language models detect misinformation in scientific news reporting?[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2402.14268.
[63] WANG L Z, XU X H, ZHANG L, et al. MMIDR: teaching large language model to interpret multimodal misinformation via knowledge distillation[EB/OL]. [2024-08-10]. https:// arxiv.org/abs/2403.14171.
[64] WEI J, ZOU K. EDA: easy data augmentation techniques for boosting performance on text classification tasks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 6381-6387.
[65] AMJAD M, SIDOROV G, ZHILA A. Data augmentation using machine translation for fake news detection in the Urdu language[C]//Proceedings of the 12th Language Resources and Evaluation Conference, 2020: 2537-2542.
[66] SALAH I, JOUINI K, KORBAA O. Augmentation-based ensemble learning for stance and fake news detection[C]//Advances in Computational Collective Intelligence. Cham: Springer, 2022: 29-41.
[67] DAHOU A H, CHERAGUI M A, ABDEDAIEM A, et al. Enhancing model performance through translation-based data augmentation in the context of fake news detection[J]. Procedia Computer Science, 2024, 244: 342-352.
[68] 蒋超, 朱学芳. 基于GPT-4数据增强与对比学习的多模态谣言检测研究[J]. 图书情报工作, 2024,68(23): 76-87.
JIANG C, ZHU X F. Research on multimodal rumor detection based on GPT-4 text augmentation and contrastive learning[J]. Library and Information Service, 2024, 68(23): 76-87.
[69] WU J Y, GUO J F, HOOI B. Fake news in sheep’s clothing: robust fake news detection against LLM-empowered style attacks[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2024: 3367-3378.
[70] WU Y, XIAO Y, HU M, et al. Towards robust evidence-aware fake news detection via improving semantic perception[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. Torino: ELRA and ICCL, 2024: 16607-16618.
[71] 姜雨杉, 张仰森. 大语言模型驱动的立场感知事实核查[J]. 计算机应用, 2024, 44(10): 3067-3073.
JIANG Y S, ZHANG Y S. Large language model-driven stance-aware fact-checking[J]. Journal of Computer Applications, 2024, 44(10): 3067-3073.
[72] WANG K, ZHU J H, REN M J, et al. A survey on data synthesis and augmentation for large language models[EB/OL]. [2024-10-30]. https://arxiv.org/abs/2410.12896.
[73] JIANG Y, WANG T H, XU X M, et al. Cross-modal augmentation for few-shot multimodal fake news detection[J]. Engineering Applications of Artificial Intelligence, 2025, 142: 109931.
[74] LIU Z C, TANG Z Q, SHI X J, et al. Learning multimodal data augmentation in feature space[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2212.14453.
[75] SI L, GUO C, LI Z, et al. A unified framework of data augmentation using large language models for text-based cross-modal retrieval[EB/OL]. [2024-08-10]. http://dx.doi.org/10.2139/ssrn.4957742.
[76] THABTAH F, HAMMOUD S, KAMALOV F, et al. Data imbalance in classification: experimental evaluation[J]. Information Sciences, 2020, 513: 429-441.
[77] JIA S, HUANG M Z, ZHOU Z, et al. AutoSplice: a text-prompt manipulated image dataset for media forensics[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2023: 893-903.
[78] YE Q H, XU H Y, YE J B, et al. mPLUG-OwI2: revolutionizing multi-modal large language model with modality collaboration[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 13040-13051.
[79] LEITE J A, RAZUVAYEVSKAYA O, BONTCHEVA K, et al. Weakly supervised veracity classification with LLM-predicted credibility signals[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2309.07601.
[80] CHERN I C, CHERN S, CHEN S Q, et al. FacTool: factuality detection in generative AI: a tool augmented framework for multi-task and multi-domain scenarios[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2307.13528.
[81] ZHANG X, GAO W. Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with black-box LLM[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. Torino: ELRA and ICCL, 2024: 13861-13873.
[82] ZHANG X, GAO W. Towards LLM-based fact verification on news claims with a hierarchical step-by-step prompting method[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2310.00305.
[83] MUTLAG W K, ALI S K, AYDAM Z M, et al. Feature extraction methods: a review[J]. Journal of Physics: Conference Series, 2020, 1591(1): 012028.
[84] WU G Y, WU W J, LIU X H, et al. Cheap-fake detection with LLM using prompt engineering[C]//Proceedings of the 2023 IEEE International Conference on Multimedia and Expo Workshops. Piscataway: IEEE, 2023: 105-109.
[85] CASTELO S, ALMEIDA T, ELGHAFARI A, et al. A topic-agnostic approach for identifying fake news pages[C]//Proceedings of the Companion of the 2019 World Wide Web Conference. New York: ACM, 2019: 975-980.
[86] LIU Y, WU Y F. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. New York:ACM, 2018: 354-361.
[87] LEE N, LI B Z, WANG S N, et al. Language models as fact checkers?[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2006. 04102.
[88] XUAN K Y, YI L, YANG F, et al. LEMMA: towards LVLM-enhanced multimodal misinformation detection with external knowledge augmentation[EB/OL]. [2024-08-13]. https://arxiv. org/abs/2402.11943.
[89] ZHOU X Y, ZAFARANI R. Network-based fake news detection: a pattern-driven approach[J]. ACM SIGKDD Explorations Newsletter, 2019, 21(2): 48-60.
[90] 杨昱洲, 周杨铭, 应祺超, 等. 基于事实信息核查的虚假新闻检测综述[J]. 中国传媒大学学报(自然科学版), 2023, 30(6): 28-36.
YANG Y Z, ZHOU Y M, YING Q C, et al. A survey on fake news detection based on fact verification[J]. Journal of Communication University of China (Science and Technology), 2023, 30(6): 28-36.
[91] DONG M W, CHRISTODOULOPOULOS C, SHIH S M, et al. Robust information retrieval for false claims with distracting entities in fact extraction and verification[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2112.07618.
[92] LIAO H, PENG J H, HUANG Z Y, et al. MUSER: a multi-step evidence retrieval enhancement framework for fake news detection[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2023: 4461-4472.
[93] YANG Z W, MA J, CHEN H C, et al. A coarse-to-fine cascaded evidence-distillation neural network for explainable fake news detection[EB/OL]. [2024-08-13]. https://arxiv.org/ abs/2209.14642.
[94] QUELLE D, BOVET A. The perils and promises of fact-checking with large language models[J]. Frontiers in Artificial Intelligence, 2024, 7: 1341697.
[95] GAO Y F, XIONG Y, GAO X Y, et al. Retrieval-augmented generation for large language models: a survey[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2312.10997.
[96] LEWIS P, PEREZ E, PIKTUS A, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks[C]//Advances in Neural Information Processing Systems 33, 2020: 9459-9474.
[97] IZACARD G, LEWIS P, LOMELI M, et al. Atlas: few-shot learning with retrieval augmented language models[J]. Journal of Machine Learning Research, 2023, 24(251): 1-43.
[98] THORNE J, VLACHOS A, COCARASCU O, et al. The fact extraction and VERification (FEVER) shared task[EB/OL]. [2024-08-13]. https://arxiv.org/abs/1811.10971.
[99] RAE J W, BORGEAUD S, CAI T, et al. Scaling language models: methods, analysis & insights from training gopher[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2112.11446.
[100] ASAI A, WU Z Q, WANG Y Z, et al. Self-RAG: learning to retrieve, generate, and critique through self-reflection[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2310.11511.
[101] SHAO Z H, GONG Y Y, SHEN Y L, et al. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2305.15294.
[102] ZAMANI H, BENDERSKY M. Stochastic RAG: end-to-end retrieval-augmented generation through expected utility maximization[C]//Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2024: 2641-2646.
[103] KHALIQ M A, CHANG P, MA M, et al. RAGAR, your falsehood radar: rag-augmented reasoning for political fact-checking using multimodal large language models[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2404.12065.
[104] TAHMASEBI S, MüLLER-BUDACK E, EWERTH R. Multimodal misinformation detection using large vision-language models[C]//Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. New York: ACM, 2024: 2189-2199.
[105] GLASS M, ROSSIELLO G, CHOWDHURY M F M, et al. Re2G: retrieve, rerank, generate[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2207.06300.
[106] HOFST?TTER S, CHEN J C, RAMAN K, et al. FiD-light: efficient and effective retrieval-augmented text generation[C]//Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2023: 1437-1447.
[107] LI G H, LU W S, ZHANG W, et al. Re-search for the truth: multi-round retrieval-augmented large language models are strong fake news detectors[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2403.09747.
[108] KHATTAB O, POTTS C, ZAHARIA M. Baleen: robust multi-hop reasoning at scale via condensed retrieval[C]//Advances in Neural Information Processing Systems 34, 2021: 27670-27682.
[109] REYNOLDS L, MCDONELL K. Prompt programming for large language models: beyond the few-shot paradigm[C]//Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2021: 1-7.
[110] DOUGREZ-LEWIS J, AKHTER M E, RUGGERI F, et al. Assessing the reasoning capabilities of LLMs in the context of evidence-based claim verification[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2402.10735.
[111] PARVEZ M R. Chain of evidences and evidence to generate: prompting for context grounded and retrieval augmented reasoning[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2401.05787.
[112] ZENG F Z, GAO W. Prompt to be consistent is better than self-consistent? few-shot and zero-shot fact verification with pre-trained language models[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2306.02569.
[113] LIU Q, TAO X, WU J F, et al. Can large language models detect rumors on social media?[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2402.03916.
[114] ZARHARAN M, WULLSCHLEGER P, KIA B B, et al. Tell me why: explainable public health fact-checking with large language models[EB/OL]. [2024-08-13]. https://arxiv. org/abs/2405.09454.
[115] PAN L M, LU X Y, KAN M Y, et al. QACHECK: a demonstration system for question-guided multi-hop fact-checking [EB/OL]. [2024-08-13]. https://arxiv.org/abs/2310.07609.
[116] CHIANG S H, LO M C, CHAO L W, et al. Team trifecta at Factify5WQA: setting the standard in fact verification with fine-tuning[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2403.10281.
[117] CHEN M, WEI L, CAO H, et al. Can large language models understand content and propagation for misinformation detection: an empirical study[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2311.12699.
[118] CAO H, WEI L W, CHEN M Y, et al. Are large language models good fact checkers: a preliminary study[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2311.17355.
[119] CAMBRIA E, MALANDRI L, MERCORIO F, et al. XAI meets LLMs: a survey of the relation between explainable AI and large language models[EB/OL]. [2024-08-13]. https:// arxiv.org/abs/2407.15248.
[120] WU X S, ZHAO H Y, ZHU Y C, et al. Usable XAI: 10 strategies towards exploiting explainability in the LLM era[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2403.08946.
[121] ADADI A, BERRADA M. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)[J]. IEEE Access, 2018, 6: 52138-52160.
[122] ANGELOV P P, SOARES E A, JIANG R, et al. Explainable artificial intelligence: an analytical review[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2021, 11(5): e1424.
[123] FU J L, NG S K, JIANG Z B, et al. GPTScore: evaluate as you desire[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2302. 04166.
[124] PENG B L, GALLEY M, HE P C, et al. Check your facts and try again: improving large language models with external knowledge and automated feedback[EB/OL]. [2024-08-13]. https://arxiv.org/abs/2302.12813.
[125] SAMEK W, MüLLER K R. Towards explainable artificial intelligence[M]//Explainable AI: interpreting, explaining and visualizing deep learning. Cham: Springer, 2019: 5-22.
[126] BARREDO ARRIETA A, DíAZ-RODRíGUEZ N, DEL SER J, et al. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI[J]. Information Fusion, 2020, 58: 82-115.
[127] WU Z Q, HU Y S, SHI W J, et al. Fine-grained human feedback gives better rewards for language model training[C]//Advances in Neural Information Processing Systems 36, 2023: 59008-59033.
[128] CUI G, YUAN L, DING N, et al. ULTRAFEEDBACK: boosting language models with scaled AI feedback[C]//Proceedings of the 41st International Conference on Machine Learning, 2024.
[129] BANERJEE T, ZHU R, YANG R Z, et al. LLMs are superior feedback providers: bootstrapping reasoning for lie detection with self-generated feedback[EB/OL]. [2024-08-30]. https://arxiv.org/abs/2408.13915.