{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T02:05:53Z","timestamp":1782439553252,"version":"3.54.5"},"reference-count":120,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["cell.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Patterns"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.patter.2026.101534","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T14:49:57Z","timestamp":1776869397000},"page":"101534","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pitfalls and risks of generative AI in machine learning"],"prefix":"10.1016","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2745-9896","authenticated-orcid":false,"given":"Michael A.","family":"Lones","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patter.2026.101534_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2024.101046","article-title":"Avoiding common machine learning pitfalls","volume":"5","author":"Lones","year":"2024","journal-title":"Patterns"},{"key":"10.1016\/j.patter.2026.101534_bib2","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adk3452","article-title":"REFORMS: Consensus-based Recommendations for Machine-learning-based Science","volume":"10","author":"Kapoor","year":"2024","journal-title":"Sci. Adv."},{"key":"10.1016\/j.patter.2026.101534_bib3","article-title":"Reproducibility in machine-learning-based research: Overview, barriers, and drivers","volume":"46","author":"Semmelrock","year":"2025","journal-title":"AI Mag."},{"key":"10.1016\/j.patter.2026.101534_bib4","doi-asserted-by":"crossref","first-page":"23661","DOI":"10.1007\/s11042-024-20016-1","article-title":"Generative artificial intelligence: A systematic review and applications","volume":"84","author":"Sengar","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.patter.2026.101534_bib5","unstructured":"Lemonne, E. Ethics Guidelines for Trustworthy AI (2018). https:\/\/ec.europa.eu\/futurium\/en\/ai-alliance-consultation."},{"key":"10.1016\/j.patter.2026.101534_bib6","article-title":"The fine art of fine-tuning: A structured review of advanced LLM fine-tuning techniques","volume":"11","author":"Pratap","year":"2025","journal-title":"Nat. Lang. Process. J."},{"key":"10.1016\/j.patter.2026.101534_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2025.101260","article-title":"Unleashing the potential of prompt engineering for large language models","volume":"6","author":"Chen","year":"2025","journal-title":"Patterns"},{"key":"10.1016\/j.patter.2026.101534_bib8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3723004","article-title":"A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook","volume":"57","author":"Sun","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patter.2026.101534_bib9","article-title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","author":"Tran","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib10","doi-asserted-by":"crossref","first-page":"6518","DOI":"10.1109\/ACCESS.2024.3349952","article-title":"A Survey of Text Classification With Transformers: How Wide? How Large? How Long? How Accurate? How Expensive? How Safe?","volume":"12","author":"Fields","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.patter.2026.101534_bib11","article-title":"Large Language Models (LLMs) on Tabular Data: Prediction, Generation, and Understanding - A Survey","author":"Fang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patter.2026.101534_bib12","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"6616","article-title":"A Survey of Large Language Models for Graphs","author":"Ren","year":"2024"},{"key":"10.1016\/j.patter.2026.101534_bib13","doi-asserted-by":"crossref","first-page":"30235","DOI":"10.1109\/ACCESS.2025.3535782","article-title":"Time-Series Large Language Models: A Systematic Review of State-of-the-Art","volume":"13","author":"Abdullahi","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.patter.2026.101534_bib14","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1093\/jamia\/ocaf038","article-title":"Large language models are less effective at clinical prediction tasks than locally trained machine learning models","volume":"32","author":"Brown","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.patter.2026.101534_bib15","article-title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","author":"Shojaee","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib16","article-title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey","author":"Subramanian","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib17","series-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. ASE \u201924","first-page":"2087","article-title":"Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patter.2026.101534_bib18","first-page":"1","article-title":"Large Language Model Supply Chain: A Research Agenda","volume":"34","author":"Wang","year":"2025","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"10.1016\/j.patter.2026.101534_bib19","series-title":"Introduction to Foundation Models","first-page":"185","article-title":"Safety Risks in Fine-Tuning Large Language Models","author":"Chen","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib20","doi-asserted-by":"crossref","first-page":"3776","DOI":"10.1109\/TASLPRO.2025.3606231","article-title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning","volume":"33","author":"Luo","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patter.2026.101534_bib21","doi-asserted-by":"crossref","first-page":"4616","DOI":"10.1109\/TCSVT.2023.3245584","article-title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","volume":"33","author":"Ma","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patter.2026.101534_bib22","article-title":"Prompt Engineering Large Language Models\u2019 Forecasting Capabilities","author":"Schoenegger","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib23","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"1543","article-title":"What Did I Do Wrong? Quantifying LLMs\u2019 Sensitivity and Consistency to Prompt Engineering","author":"Errica","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib24","article-title":"A Survey on Data Contamination for Large Language Models","author":"Cheng","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib25","article-title":"Recent Advances in Large Language Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","author":"Chen","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib26","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1162\/TACL.a.20","article-title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","volume":"13","author":"Golchin","year":"2025","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.patter.2026.101534_bib27","article-title":"Position: Editing Large Language Models Poses Serious Safety Risks","author":"Youssef","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib28","article-title":"Pitfalls in Evaluating Language Model Forecasters","author":"Paleka","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib29","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"12067","article-title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","author":"He","year":"2023"},{"key":"10.1016\/j.patter.2026.101534_bib30","article-title":"Metrics that matter: Evaluating image quality metrics for medical image generation","author":"Deo","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib31","series-title":"Proceedings of the 30th International Conference on Intelligent User Interfaces","first-page":"952","article-title":"Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks","author":"Szymanski","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib32","article-title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","author":"Li","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib33","series-title":"AI Strategy and Security: A Roadmap for Secure, Responsible, and Resilient AI Adoption","first-page":"137","article-title":"Regulations, Standards, and Frameworks","author":"Wendt","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib34","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s10462-024-10916-x","article-title":"Explainable Generative AI (GenXAI): A survey, conceptualization, and research agenda","volume":"57","author":"Schneider","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patter.2026.101534_bib35","article-title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","author":"Zhao","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib36","series-title":"MultiMedia Modeling","first-page":"184","article-title":"The Right to an Explanation Under the GDPR and the AI Act","author":"Juliussen","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3728637","article-title":"Ante-Hoc Methods for Interpretable Deep Models: A Survey","volume":"57","author":"Di Marino","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patter.2026.101534_bib38","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1038\/s42256-024-00857-z","article-title":"Systematic analysis of 32,111 AI model cards characterizes documentation practice in AI","volume":"6","author":"Liang","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patter.2026.101534_bib39","article-title":"Blueprints of Trust: AI System Cards for End to End Transparency and Governance","author":"Sidhpurwala","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib40","article-title":"Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions","author":"Bisconti","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib41","article-title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","author":"Reid","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib42","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.patter.2026.101534_bib43","article-title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","author":"Chen","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib44","article-title":"Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem","author":"Gaire","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib45","article-title":"Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents","author":"Narajala","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib46","series-title":"2025 IEEE International Conference on Artificial Intelligence Testing (AITest)","first-page":"69","article-title":"Surveying the RAG Attack Surface and Defenses: Protecting Sensitive Company Data","author":"Vonderhaar","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib47","article-title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","author":"Gu","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3744238","article-title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","volume":"58","author":"Shorinwa","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patter.2026.101534_bib49","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1145\/3715073.3715077","article-title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","volume":"26","author":"Li","year":"2025","journal-title":"SIGKDD Explor. Newsl."},{"key":"10.1016\/j.patter.2026.101534_bib50","article-title":"Forget What You Know about LLMs Evaluations \u2013 LLMs are Like a Chameleon","author":"Cohen-Inger","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib51","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10664-025-10614-4","article-title":"Bugs in large language models generated code: An empirical study","volume":"30","author":"Tambon","year":"2025","journal-title":"Empir. Softw. Eng."},{"key":"10.1016\/j.patter.2026.101534_bib52","article-title":"Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education","author":"Kumar","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib53","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis in machine-learning-based science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"key":"10.1016\/j.patter.2026.101534_bib54","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2024.107610","article-title":"Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forward","volume":"178","author":"Sergeyuk","year":"2025","journal-title":"Inf. Software Technol."},{"key":"10.1016\/j.patter.2026.101534_bib55","doi-asserted-by":"crossref","DOI":"10.63383\/hadW7619","article-title":"The Hidden Costs of Coding With Generative AI","volume":"67","author":"Anderson","year":"2025","journal-title":"MIT Sloan Manag. Rev."},{"key":"10.1016\/j.patter.2026.101534_bib56","series-title":"2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR)","first-page":"27","article-title":"Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries","author":"Harzevili","year":"2023"},{"key":"10.1016\/j.patter.2026.101534_bib57","article-title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","author":"Spracklen","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib58","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s12559-024-10373-2","article-title":"eXplainable AI for Word Embeddings: A Survey","volume":"17","author":"Boselli","year":"2024","journal-title":"Cognit. Comput."},{"key":"10.1016\/j.patter.2026.101534_bib59","article-title":"Anisotropy Is Inherent to Self-Attention in Transformers","author":"Godey","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib60","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10462-024-11024-6","article-title":"Generative AI model privacy: A survey","volume":"58","author":"Liu","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patter.2026.101534_bib61","unstructured":"European Research Area Forum. Guidelines on the responsible use of generative AI in research developed by the European Research Area Forum - European Commission (2025). https:\/\/research-and-innovation.ec.europa.eu\/news\/all-research-and-innovation-news\/guidelines-responsible-use-generative-ai-research-developed-european-research-area-forum-2024-03-20_en."},{"key":"10.1016\/j.patter.2026.101534_bib62","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1007\/s43681-024-00493-8","article-title":"The ethics of using artificial intelligence in scientific research: New guidance needed for a new tool","volume":"5","author":"Resnik","year":"2025","journal-title":"AI Ethics"},{"key":"10.1016\/j.patter.2026.101534_bib63","article-title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","author":"Guo","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib64","article-title":"A Survey on Data Augmentation in Large Model Era","author":"Zhou","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib65","doi-asserted-by":"crossref","first-page":"3909","DOI":"10.3390\/electronics13193909","article-title":"Bias Mitigation via Synthetic Data Generation: A Review","volume":"13","author":"Shahul Hameed","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.patter.2026.101534_bib66","article-title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead","author":"Schlegel","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib67","series-title":"Forty-First International Conference on Machine Learning","article-title":"Data Authenticity, Consent, & Provenance for AI are all broken: What will it take to fix them?","author":"Longpre","year":"2024"},{"key":"10.1016\/j.patter.2026.101534_bib68","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1038\/s42256-024-00878-8","article-title":"A large-scale audit of dataset licensing and attribution in AI","volume":"6","author":"Longpre","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patter.2026.101534_bib69","article-title":"Copyright Protection in Generative AI: A Technical Perspective","author":"Ren","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib70","doi-asserted-by":"crossref","first-page":"15795","DOI":"10.1109\/ACCESS.2025.3532128","article-title":"Comprehensive Review of Privacy, Utility, and Fairness Offered by Synthetic Data","volume":"13","author":"Kiran","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.patter.2026.101534_bib71","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108571","article-title":"Preserving privacy in healthcare: A systematic review of deep learning approaches for synthetic data generation","volume":"260","author":"Liu","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.patter.2026.101534_bib72","article-title":"Medical imaging privacy: A systematic scoping review of key parameters in dataset construction and data protection","volume":"56","author":"Rachel","year":"2025","journal-title":"J. Med. Imag. Radiat. Sci."},{"key":"10.1016\/j.patter.2026.101534_bib73","article-title":"Differential Privacy in Machine Learning: From Symbolic AI to LLMs","author":"Aguilera-Mart\u00ednez","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib74","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1162\/coli_a_00524","article-title":"Bias and Fairness in Large Language Models: A Survey","volume":"50","author":"Gallegos","year":"2024","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.patter.2026.101534_bib75","article-title":"Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","author":"Li","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib76","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1013080","article-title":"Generative AI mitigates representation bias and improves model fairness through synthetic health data","volume":"21","author":"Marchesi","year":"2025","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.patter.2026.101534_bib77","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3616865","article-title":"Fairness in Machine Learning: A Survey","volume":"56","author":"Caton","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patter.2026.101534_bib78","series-title":"KI 2025: Advances in Artificial Intelligence: 48th German Conference on AI, Potsdam, Germany, September 16\u201319, 2025, Proceedings","first-page":"175","article-title":"Development of Hybrid Artificial Intelligence Training on Real and Synthetic Data: Benchmark on Two Mixed Training Strategies","author":"Wachter","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib79","doi-asserted-by":"crossref","DOI":"10.1136\/bmjebm-2024-113617","article-title":"Understanding synthetic data: Artificial datasets for real-world evidence","author":"Foraker","year":"2025","journal-title":"BMJ Evid. Based. Med."},{"key":"10.1016\/j.patter.2026.101534_bib80","article-title":"Spurious Correlations in Machine Learning: A Survey","author":"Ye","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib81","article-title":"Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)","author":"Xu","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib82","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"4645","article-title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","author":"Tang","year":"2023"},{"key":"10.1016\/j.patter.2026.101534_bib83","article-title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","author":"Long","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib84","series-title":"Human-Computer Interaction","first-page":"190","article-title":"Automatic Prompt Optimization Techniques: Exploring the Potential for Synthetic Data Generation","author":"Freise","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib85","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1038\/s41586-024-07566-y","article-title":"AI models collapse when trained on recursively generated data","volume":"631","author":"Shumailov","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.patter.2026.101534_bib86","article-title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","author":"Chen","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib87","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41746-024-01359-3","article-title":"A scoping review of privacy and utility metrics in medical synthetic data","volume":"8","author":"Kaabachi","year":"2025","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.patter.2026.101534_bib88","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1145\/3706101","article-title":"Crowdsourcing or AI Sourcing?","volume":"68","author":"Christoforou","year":"2025","journal-title":"Commun. ACM"},{"key":"10.1016\/j.patter.2026.101534_bib89","article-title":"Mitigating Label Biases for In-context Learning","author":"Fei","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib90","article-title":"Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System","author":"Ma","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib91","first-page":"62697","article-title":"Are Large Language Models Good Statisticians?","volume":"37","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2026.101534_bib92","doi-asserted-by":"crossref","first-page":"9303","DOI":"10.1109\/TVCG.2025.3542504","article-title":"Leveraging Foundation Models for Crafting Narrative Visualization: A Survey","volume":"31","author":"He","year":"2025","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.patter.2026.101534_bib93","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40763-6","article-title":"Large language model for table processing: A survey","volume":"19","author":"Lu","year":"2025","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.patter.2026.101534_bib94","article-title":"Mapping the Increasing Use of LLMs in Scientific Papers","author":"Liang","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib95","article-title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","author":"Nikankin","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib96","article-title":"Implicit Reasoning in Transformers is Reasoning through Shortcuts","author":"Lin","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib97","article-title":"The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination","author":"Yin","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib98","article-title":"Tools Fail: Detecting Silent Errors in Faulty Tools","author":"Sun","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib99","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317084","article-title":"Leveraging large language models for data analysis automation","volume":"20","author":"Jansen","year":"2025","journal-title":"PLoS One"},{"key":"10.1016\/j.patter.2026.101534_bib100","series-title":"2024 IEEE 17th Pacific Visualization Conference (PacificVis)","first-page":"343","article-title":"Are LLMs ready for Visualization?","author":"V\u00e1zquez","year":"2024"},{"key":"10.1016\/j.patter.2026.101534_bib101","first-page":"1","article-title":"Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature","volume":"9","author":"Zhang","year":"2025","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"10.1016\/j.patter.2026.101534_bib102","doi-asserted-by":"crossref","unstructured":"Kadenhe, N., Al Musleh, M., and Lompot, A. (2025). Human-AI Co-Design and Co-Creation: A Review of Emerging Approaches, Challenges, and Future Directions. Proceedings of the AAAI Symposium Series 6, 265\u2013270. https:\/\/doi.org\/10.1609\/aaaiss.v6i1.36061.","DOI":"10.1609\/aaaiss.v6i1.36061"},{"key":"10.1016\/j.patter.2026.101534_bib103","doi-asserted-by":"crossref","first-page":"8317","DOI":"10.1038\/s41467-025-63913-1","article-title":"Risks of AI scientists: Prioritizing safeguarding over autonomy","volume":"16","author":"Tang","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.patter.2026.101534_bib104","article-title":"Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","author":"Xiong","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib105","doi-asserted-by":"crossref","DOI":"10.1056\/AIe2401073","article-title":"The Promise and Perils of Autonomous AI in Science","volume":"2","author":"Gao","year":"2025","journal-title":"NEJM AI"},{"key":"10.1016\/j.patter.2026.101534_bib106","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1038\/s44319-025-00424-6","article-title":"Gen AI and research integrity: Where to now?","volume":"26","author":"Vasconcelos","year":"2025","journal-title":"EMBO Rep."},{"key":"10.1016\/j.patter.2026.101534_bib107","article-title":"Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task","author":"Kosmyna","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib108","series-title":"Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems","first-page":"1","article-title":"Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits","author":"Chakrabarty","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib109","series-title":"20th International Conference on Scientometrics & Informetrics","doi-asserted-by":"crossref","DOI":"10.51408\/issi2025_035","article-title":"How Much are LLMs Changing the Language of Academic Papers?","author":"Kousha","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib110","article-title":"Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback","author":"Juzek","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib111","doi-asserted-by":"crossref","DOI":"10.1038\/d41586-025-03664-7","article-title":"Preprint site arXiv is banning computer-science reviews: Here\u2019s why","author":"Castelvecchi","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.patter.2026.101534_bib112","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"1602","article-title":"Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition","author":"Tang","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib113","doi-asserted-by":"crossref","first-page":"7004","DOI":"10.1109\/TVCG.2025.3536358","article-title":"Do LLMs Have Visualization Literacy? An Evaluation on Modified Visualizations to Test Generalization in Data Interpretation","volume":"31","author":"Hong","year":"2025","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.patter.2026.101534_bib114","series-title":"Intelligent Systems and Applications","first-page":"656","article-title":"Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work","author":"Jain","year":"2024"},{"key":"10.1016\/j.patter.2026.101534_bib115","article-title":"Multi-Agent Risks from Advanced AI","author":"Hammond","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib116","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1007\/s10796-024-10508-8","article-title":"Making It Possible for the Auditing of AI: A Systematic Review of AI Audits and AI Auditability","volume":"27","author":"Li","year":"2025","journal-title":"Inf. Syst. Front."},{"key":"10.1016\/j.patter.2026.101534_bib117","series-title":"2025 1st International Conference on Computational Intelligence Approaches and Applications (ICCIAA)","first-page":"1","article-title":"Concept Drift in Large Language Models: Challenges of Evolving Language, Contexts, and the Web","author":"Hajmohammed","year":"2025"},{"key":"10.1016\/j.patter.2026.101534_bib118","series-title":"Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization. EAAMO \u201923","first-page":"1","article-title":"A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems","author":"Pagan","year":"2023"},{"key":"10.1016\/j.patter.2026.101534_bib119","article-title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","author":"Shayegani","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101534_bib120","article-title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","author":"Vinay","year":"2025","journal-title":"arXiv"}],"container-title":["Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389926000437?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389926000437?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:09:08Z","timestamp":1778252948000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666389926000437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":120,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["S2666389926000437"],"URL":"https:\/\/doi.org\/10.1016\/j.patter.2026.101534","relation":{},"ISSN":["2666-3899"],"issn-type":[{"value":"2666-3899","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Pitfalls and risks of generative AI in machine learning","name":"articletitle","label":"Article Title"},{"value":"Patterns","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patter.2026.101534","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"101534"}}