A survey of safety and trustworthiness of large language models through the lens of verification and validation
Open accessThe DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Abstract
Large language models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and deep learning models such as convolutional neural networks as independent processes to check the alignment of their implementations against the specifications, can be integrated and further extended throughout the lifecycle of the LLMs to provide rigorous analysis to the safety and trustworthiness of LLMs and their applications. Specifically, we consider four complementary techniques: falsification and evaluation, verification, runtime monitoring, and regulations and ethical use. In total, 370+ references are considered to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V. While intensive research has been conducted to identify the safety and trustworthiness issues, rigorous yet practical methods are called for to ensure the alignment of LLMs with safety and trustworthiness requirements.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Generative adversarial networks
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020) · Communications of the ACM · doi:10.1145/3422622 · Cited by 18,384
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“[142] demonstrated that simply increasing the size of T-PTLMs can lead to improved performance [138].”
BackgroundLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“The well-known text-based LLMs include GPT-1 [254], BERT [98], XLNet [347], RoBERTa [219], ELECTRA [85], T5 [256], ALBERT [193], BART [201], and PEGASUS [360].”
MethodIntriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
de Moura, L., & Bjørner, N. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-78800-3_24 · Cited by 6,595
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · cited 2×
“The well-known text-based LLMs include GPT-1 [254], BERT [98], XLNet [347], RoBERTa [219], ELECTRA [85], T5 [256], ALBERT [193], BART [201], and PEGASUS [360].”
MethodChain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
Deep Learning for Anomaly Detection: A Review
Pang, G., Shen, C., Cao, L., & Hengel, A. V. D. (2022) · ACM Computing Surveys · doi:10.1145/3439950 · Cited by 2,837
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2020) · arXiv · doi:10.48550/arxiv.2012.09841 · Cited by 2,514
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514 · cited 2×
“Parti [353] demonstrates that a VQGAN [111] and Transformer architecture can achieve superior image synthesis outcomes compared to previous approaches, even without utilising a diffusion model.”
MethodParameter-efficient transfer learning for NLP
Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Gesmundo, A., Attariyan, M., & Gelly, S. (2019) · arXiv · doi:10.48550/arxiv.1902.00751 · Cited by 2,270
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
XAI—Explainable artificial intelligence
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, G.-Z. (2019) · Science Robotics · doi:10.1126/scirobotics.aay7120 · Cited by 2,053
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1610.02136 · Cited by 1,968
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410 · cited 1×
“In addition, in sentence level adversarial attacks, some attacks [133, 256] are created so that they do not impact the original label of the input and can be incorporated as a concatenation in the original text.”
BackgroundUnifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357 · cited 2×
“GLIDE [187] employs a transformer model [247] to encode the text input and then trains a diffusion model to generate images that are conditioned on the text tokens directly .”
MethodFEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 1×
“Regarding factual errors, [242] proposed a testbed for fact verification.”
BackgroundBadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238 · cited 1×
“Backdoor attack on DL models is firstly introduced on image classification tasks [106], in which the attacker can use a patch/watermark as a trigger and train a backdoored model from scratch.”
BackgroundSummary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.01852 · Cited by 1,172
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Fedus, W., Zoph, B., & Shazeer, N. (2021) · arXiv · doi:10.48550/arxiv.2101.03961 · Cited by 1,005
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929
Generalized Out-of-Distribution Detection: A Survey
Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02117-4 · Cited by 884
LaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778
Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges
Xu, F., Uszkoreit, H., Du, Y., Fan, W., Zhao, D., & Zhu, J. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32236-6_51 · Cited by 758
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.759 · Cited by 755
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022) · arXiv · doi:10.48550/arxiv.2202.12837 · Cited by 752
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
Gao, J., Lanchantin, J., Soffa, M. L., & Qi, Y. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00016 · Cited by 693
Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al. (2023) · Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.ijcnlp-main.45 · Cited by 682
Adversarial NLI: A New Benchmark for Natural Language Understanding
Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., & Kiela, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.441 · Cited by 656
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., Yin, B., & Hu, X. (2023) · arXiv · doi:10.48550/arxiv.2304.13712 · Cited by 644
Detecting Adversarial Samples from Artifacts
Feinman, R., Curtin, R. R., Shintre, S., & Gardner, A. B. (2017) · arXiv · doi:10.48550/arxiv.1703.00410 · Cited by 606
Galactica: A Large Language Model for Science
Taylor, R., Kardas, M., Cucurull, G., Scialom, T., Hartshorn, A., Saravia, E., Poulton, A., Kerkez, V., & Stojnic, R. (2022) · arXiv · doi:10.48550/arxiv.2211.09085 · Cited by 605
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · doi:10.21203/rs.3.rs-2895792/v1 · Cited by 514
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · arXiv · doi:10.48550/arxiv.2302.03494 · Cited by 514
Generating Natural Adversarial Examples
Zhao, Z., Dua, D., & Singh, S. (2017) · arXiv · doi:10.48550/arxiv.1710.11342 · Cited by 508 · cited 1×
“Another approach [294] involves generating sentence-level adversaries using GANs (generative adversarial networks) [99], which produce outputs that are both grammatically correct and semantically similar to the input text.”
BackgroundKatz, D. M., Bommarito, M. J., Gao, S., & Arredondo, P. (2024) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2023.0254 · Cited by 420
Benchmarking Large Language Models for News Summarization
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., & Hashimoto, T. B. (2023) · arXiv · doi:10.48550/arxiv.2301.13848 · Cited by 415 · cited 1×
“LLMs have been applied to many tasks, such as text generation [205], content summary [362], conversational AI (i.”
MethodFine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
Dodge, J., Ilharco, G., Schwartz, R., Farhadi, A., Hajishirzi, H., & Smith, N. (2020) · arXiv · doi:10.48550/arxiv.2002.06305 · Cited by 412
The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink
Patterson, D., Gonzalez, J., Holzle, U., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D., So, D. R., Texier, M., & Dean, J. (2022) · Computer · doi:10.1109/mc.2022.3148714 · Cited by 400
Liu, J., Xia, C. S., Wang, Y., & Zhang, L. (2023) · arXiv · doi:10.48550/arxiv.2305.01210 · Cited by 390 · cited 1×
“As we mentioned in previous sections, although LLMs have shown strong performance in many domains [38, 174, 136, 231, 295], they are also found to be prone to various types of failures after scrutiny and evaluation [47, 225, 290], such as factual errors [290], coding [171, 144], math [94], and reasoning [170].”
BackgroundScaling Autoregressive Models for Content-Rich Text-to-Image Generation
Yu, J., Xu, Y., Koh, J. Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B. K., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.10789 · Cited by 371
Large language models are few-shot clinical information extractors
Agrawal, M., Hegselmann, S., Lang, H., Kim, Y., & Sontag, D. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.130 · Cited by 358
Weight Poisoning Attacks on Pretrained Models
Kurita, K., Michel, P., & Neubig, G. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.249 · Cited by 354
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, X., Nie, J.-Y., & Wen, J.-R. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.397 · Cited by 343
Self-citationA Review of User Interface Design for Interactive Machine Learning
Dudley, J. J., & Kristensson, P. O. (2018) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3185517 · Cited by 343
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, W. X., Nie, J.-Y., & Wen, J.-R. (2023) · arXiv · doi:10.48550/arxiv.2305.11747 · Cited by 340 · cited 1×
“1 Factual errors Factual errors refer to situations where the output of an LLM contradicts the truth, where some literature refers this situation as hallucination [240][365][203].”
BackgroundMalinka, K., Peresíni, M., Firc, A., Hujnák, O., & Janus, F. (2023) · Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1 · doi:10.1145/3587102.3588827 · Cited by 287
Up or Down? Adaptive Rounding for Post-Training Quantization
Nagel, M., Amjad, R. A., van Baalen, M., Louizos, C., & Blankevoort, T. (2020) · arXiv · doi:10.48550/arxiv.2004.10568 · Cited by 252
Use of Artificial Intelligence Chatbots for Cancer Treatment Information
Chen, S., Kann, B. H., Foote, M. B., Aerts, H. J. W. L., Savova, G. K., Mak, R. H., & Bitterman, D. S. (2023) · JAMA Oncology · doi:10.1001/jamaoncol.2023.2954 · Cited by 251
Calibration of Pre-trained Transformers
Desai, S., & Durrett, G. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.21 · Cited by 209
Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physics
Holmes, J., Liu, Z., Zhang, L., Ding, Y., Sio, T. T., McGee, L. A., Ashman, J. B., Li, X., Liu, T., Shen, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.01938 · Cited by 190
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Sun, Y., Wang, S., Feng, S., Ding, S., Pang, C., Shang, J., Liu, J., Chen, X., Zhao, Y., Lu, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.02137 · Cited by 186
Peng, B., Li, C., He, P., Galley, M., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2304.03277 · Cited by 183
Toxicity in chatgpt: Analyzing persona-assigned language models
Deshpande, A., Murahari, V., Rajpurohit, T., Kalyan, A., & Narasimhan, K. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.88 · Cited by 178
The Self-Perception and Political Biases of ChatGPT
Rutinowski, J., Franke, S., Endendyk, J., Dormuth, I., & Pauly, M. (2023) · arXiv · doi:10.48550/arxiv.2304.07333 · Cited by 178 · cited 2×
“A political compass test [271] reveals that ChatGPT is biased towards progressive and libertarian views.”
BackgroundToxicity in ChatGPT: Analyzing Persona-assigned Language Models
Deshpande, A., Murahari, V., Rajpurohit, T., Kalyan, A., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2304.05335 · Cited by 178
Zeng, W., Ren, X., Su, T., Wang, H., Liao, Y., Wang, Z., Jiang, X., Yang, Z., Wang, K., Zhang, X., et al. (2021) · arXiv · doi:10.48550/arxiv.2104.12369 · Cited by 172
Self-citationCan ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT
Zhong, Q., Ding, L., Liu, J., Du, B., & Tao, D. (2023) · arXiv · doi:10.48550/arxiv.2302.10198 · Cited by 146
Towards Verified Artificial Intelligence
Seshia, S. A., Sadigh, D., & Sastry, S. S. (2016) · arXiv · doi:10.48550/arxiv.1606.08514 · Cited by 142 · cited 1×
“To overcome these limitations, another class of techniques has emerged, grounded in the concept of "certification" or "verification" [222, 126].”
Method(2023) · doi:10.1109/sp46215.2023.10179324 · Cited by 131
Hidden Backdoors in Human-Centric Language Models
Li, S., Liu, H., Dong, T., Zhao, B. Z. H., Xue, M., Zhu, H., & Lu, J. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484576 · Cited by 119 · cited 1×
“3 Expression of Backdoor In contrast to prior works that concentrate on backdoor attacks in text classification tasks, the applicability of backdoor attacks is investigated in more complex downstream NLP tasks such as toxic comment detection, Neural Machine Translation (NMT), and Question Answer (QA) [206] .”
BackgroundExploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Kang, D., Li, X., Stoica, I., Guestrin, C., Zaharia, M., & Hashimoto, T. (2024) · 2024 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw63631.2024.00018 · Cited by 114 · cited 1×
“[140] explores the programmatic behaviour of LLMs, demonstrating that classical security attacks such as obfuscation, code injection, and virtualisation can be used to circumvent the defence mechanisms of LLMs.”
BackgroundExploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Kang, D., Li, X., Stoica, I., Guestrin, C., Zaharia, M., & Hashimoto, T. (2023) · arXiv · doi:10.48550/arxiv.2302.05733 · Cited by 114 · cited 1×
“[140] explores the programmatic behaviour of LLMs, demonstrating that classical security attacks such as obfuscation, code injection, and virtualisation can be used to circumvent the defence mechanisms of LLMs.”
BackgroundLarge Language Models are Better Reasoners with Self-Verification
Weng, Y., Zhu, M., Xia, F., Li, B., He, S., Liu, S., Sun, B., Liu, K., & Zhao, J. (2022) · arXiv · doi:10.48550/arxiv.2212.09561 · Cited by 110 · cited 1×
“Figure 6: Example of Self-Verification proposed in [259].”
BackgroundIgnore Previous Prompt: Attack Techniques For Language Models
Perez, F., & Ribeiro, I. (2022) · arXiv · doi:10.48550/arxiv.2211.09527 · Cited by 110 · cited 2×
“, prompt injection [195] or prompt leaking [18] that we will discuss in Section 5.”
BackgroundCan an artificial intelligence chatbot be the author of a scholarly article?
Lee, J. Y. (2023) · Journal of Educational Evaluation for Health Professions · doi:10.3352/jeehp.2023.20.6 · Cited by 108
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Wang, B., Xu, C., Wang, S., Gan, Z., Cheng, Y., Gao, J., Awadallah, A. H., & Li, B. (2021) · arXiv · doi:10.48550/arxiv.2111.02840 · Cited by 88
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective
Wang, J., Hu, X., Hou, W., Chen, H., Zheng, R., Wang, Y., Yang, L., Huang, H., Ye, W., Geng, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.12095 · Cited by 86
Self-citationIn ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
Shen, X., Chen, Z., Backes, M., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2304.08979 · Cited by 76 · cited 3×
“For example, [225] shows that ChatGPT significantly under-performs in law and science questions.”
BackgroundSelf-citationGPT-NeoX-20B: An Open-Source Autoregressive Language Model
Black, S., Biderman, S., Hallahan, E., Anthony, Q., Gao, L., Golding, L., He, H., Leahy, C., McDonell, K., Phang, J., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.06745 · Cited by 67
Ramamurthy, R., Ammanabrolu, P., Brantley, K., Hessel, J., Sifa, R., Bauckhage, C., Hajishirzi, H., & Choi, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.01241 · Cited by 56
Fundamental Limitations of Alignment in Large Language Models
Wolf, Y., Wies, N., Avnery, O., Levine, Y., & Shashua, A. (2023) · arXiv · doi:10.48550/arxiv.2304.11082 · Cited by 47
Safe Reinforcement Learning via Shielding
Alshiekh, M., Bloem, R., Ehlers, R., Könighofer, B., Niekum, S., & Topcu, U. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11797 · Cited by 37
On the Decision Boundary of Deep Neural Networks
Li, Y., Ding, L., & Gao, X. (2018) · arXiv · doi:10.48550/arxiv.1808.05385 · Cited by 31 · cited 1×
“, some critical layers of the LLMs or the output [164, 62].”
Background
Cited by
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
Self-citationThe rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
“Ensuring trustworthiness has consistently remained a critically important yet challenging issue within the field of deep learning [535–537].”
Self-citationA Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Kalyan, K. S. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100048 · Cited by 335
AI agents under threat: A survey of key security challenges and future pathways
Deng, Z., Guo, Y., Han, C., Ma, W., Xiong, J., Wen, S., & Xiang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3716628 · Cited by 210
Ai-Based Chatbot Interactions and Critical Thinking Skills: An Exploratory Study
Fabio, R. A., Plebe, A., & Suriano, R. (2025) · Current Psychology · doi:10.1007/s12144-024-06795-8 · Cited by 49
“For example, if a user asks for detailed explanations on a complex topic, ChatGPT might generate an explanation that seems accurate but is incomplete or incorrect (Huang et al., 2024).”
Metadata
- Authors
- Huang, X., Ruan, W., Huang, W., Jin, G., Dong, Y., Wu, C., Bensalem, S., Mu, R., Qi, Y., Zhao, X., Cai, K., Zhang, Y., Wu, S., Xu, P., Wu, D., Freitas, A., & Mustafa, M. A.
- Venue
- Artificial Intelligence Review
- Published
- 2024-06-17
- Volume
- 57
- Issue
- 7
- ISSN
- 0269-2821 (ISSN-L)
- 1573-7462
- OpenAlex
- W4399750638
- Cited by
- 158
- References
- 82
- FWCI
- 40.19
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.