AI到底是怎么骗人的？
参考文献：
[1] AI Overviews: About last week[EB/OL]. (2024-05-30)
[2] 语言模型为何会产生幻觉[EB/OL]. (2026-04-23)
[3] LIN S, HILTON J, EVANS O. TruthfulQA: Measuring How Models Mimic Human Falsehoods[EB/OL]. arXiv, 2022
[4] LEWIS P, PEREZ E, PIKTUS A, et al,. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks[EB/OL]. arXiv, 2021.
[5] MALLEN A, ASAI A, ZHONG V, et al,. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories[EB/OL]. arXiv, 2023.
[6] PEREZ E, RINGER S, LUKOŠIŪTĖ K, et al,. Discovering Language Model Behaviors with Model-Written Evaluations[EB/OL]. arXiv, 2022.
[7] Sycophancy in GPT-4o: What happened and what we’re doing about it[EB/OL].
[8] SHARMA M, TONG M, KORBAK T, et al,. Towards Understanding Sycophancy in Language Models[EB/OL]. arXiv, 2025.
[9] o3-and-o4-mini-system-card.pdf[EB/OL].
[10] CHEN Y, BENTON J, RADHAKRISHNAN A, et al,. Reasoning Models Don’t Always Say What They Think[EB/OL]. arXiv, 2025
[11] Gemini image generation got it wrong. We’ll do better.[EB/OL]. (2024-02-23)
[12] KLEINBERG J, MULLAINATHAN S, RAGHAVAN M. Inherent Trade-Offs in the Fair Determination of Risk Scores[EB/OL]. arXiv, 2016
[13] HUBINGER E, DENISON C, MU J, et al,. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training[EB/OL]. arXiv, 2024
