Scalable Oversight 入门

参考文献

全书引用的全部文献。每条后面链接到引用它的小节。未经同行评审的文献带有标记:预印本、工作论文、软件、非同行评审。作者后面括号里的年份是首次公开的年份;后来在另一年的会议或期刊上发表的,那一年写在会议或期刊名的后面。

A

  1. Achiam, J. (2018). Spinning Up in Deep Reinforcement Learning. OpenAI. 非同行评审 第 6 章
  2. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., and Mané, D. (2016). Concrete Problems in AI Safety. arXiv. 预印本 §7.1 第 7 章 §8.2 §11.8 第 11 章
  3. Anthropic (2024). Mapping the mind of a large language model. Anthropic. 非同行评审 §18.7 第 18 章
  4. Anthropic (2026). Automated Alignment Researchers: Using large language models to scale scalable oversight. Anthropic. 非同行评审 §23.4 第 29 章 §29.2 §29.5 第 29 章 §D.2
  5. Arnesen, S., Rein, D., and Michael, J. (2024). Training Language Models to Win Debates with Self-Play Improves Judge Accuracy. arXiv. 预印本 第 15 章 §15.4 §15.5 第 15 章 §23.4

B

  1. Baack, S. (2024). A Critical Analysis of the Largest Source for Generative AI Training Data: Common Crawl. The 2024 ACM Conference on Fairness, Accountability, and Transparency. §24.2
  2. Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., … Kaplan, J. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv. 预印本 §6.3 §6.4 第 21 章 §21.1 §21.3 §21.5 第 21 章 §22.1
  3. Bainbridge, L. (1983). Ironies of automation. Automatica. §13.2 §13.3
  4. Baker, B., Huizinga, J., Gao, L., Dou, Z., Guan, M. Y., Madry, A., … Farhi, D. (2025). Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation. arXiv. 预印本 第 8 章 §8.7 第 19 章 §19.4 §19.5 §19.7 第 19 章 第 20 章 §20.2 §20.4 第 20 章 §22.1 §22.3 第 23 章 §23.4 §23.5 第 23 章 第 31 章
  5. Barnes, B. (2020). Debate update: Obfuscated arguments problem. AI Alignment Forum. 非同行评审 §14.6 §15.10 第 15 章
  6. Bean, A. M., Kearns, R. O., Romanou, A., Hafner, F. S., Mayne, H., Batzner, J., … Mahdi, A. (2025). Measuring what Matters: Construct Validity in Large Language Model Benchmarks. Advances in Neural Information Processing Systems 38. §11.6 第 11 章
  7. Belinkov, Y. (2021). Probing Classifiers: Promises, Shortcomings, and Advances. Computational Linguistics, 2022. §18.2 §18.3 §18.7 第 18 章
  8. Bhatt, A., Rushing, C., Kaufman, A., Tracy, T., Georgiev, V., Matolcsi, D., Khan, A., and Shlegeris, B. (2025). Ctrl-Z: Controlling AI Agents via Resampling. arXiv. 预印本 第 26 章 §26.3 §26.4 §26.5 §26.6 第 26 章 第 26 章
  9. Blitzstein, J. K., and Hwang, J. (2019). Introduction to Probability. Chapman and Hall/CRC. 第 3 章
  10. BlueDot Impact (2026a). Technical AI Safety. BlueDot Impact. 非同行评审 §C.2
  11. BlueDot Impact (2026b). The Future of AI. BlueDot Impact. 非同行评审 第 1 章 §C.2
  12. Bowkis, A., Buhl, M. D., Pfau, J., and Irving, G. (2026). Automated alignment is harder than you think. arXiv. 预印本 §29.5
  13. Bowman, S. R., Hyun, J., Perez, E., Chen, E., Pettit, C., Heiner, S., … Kaplan, J. (2022). Measuring Progress on Scalable Oversight for Large Language Models. arXiv. 预印本 §7.1 第 7 章 第 7 章 §11.1 §11.2 §11.3 §11.4 §11.5 §11.6 第 11 章 第 11 章 §13.1 §13.4 §13.6 §28.1
  14. Bricken, T., Wang, R., Bowman, S., Ong, E., Treutlein, J., Wu, J., Hubinger, E., and Marks, S. (2025). Building and evaluating alignment auditing agents. Anthropic Alignment Science Blog. 非同行评审 第 27 章 §27.2 §27.3 §27.4 第 27 章
  15. Brown-Cohen, J., Irving, G., and Piliouras, G. (2023). Scalable AI Safety via Doubly-Efficient Debate. International Conference on Machine Learning, 2024. §15.7 §15.8 §15.9 第 15 章
  16. Brown-Cohen, J., Irving, G., and Piliouras, G. (2025). Avoiding Obfuscation with Prover-Estimator Debate. arXiv. 预印本 §15.9 §15.10 §15.11 第 15 章 §D.2
  17. Buhl, M. D., Pfau, J., Hilton, B., and Irving, G. (2025). An alignment safety case sketch based on debate. arXiv. 预印本 §15.6 §28.3 第 29 章 §29.5 第 31 章 §31.2 §31.3 第 31 章
  18. Burns, C., Ye, H., Klein, D., and Steinhardt, J. (2022). Discovering Latent Knowledge in Language Models Without Supervision. International Conference on Learning Representations, 2023. 第 18 章 §18.5 第 18 章 第 18 章 §22.1
  19. Burns, C., Izmailov, P., Kirchner, J. H., Baker, B., Gao, L., Aschenbrenner, L., … Wu, J. (2023). Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision. International Conference on Machine Learning, 2024. §6.1 §7.7 §11.3 第 17 章 §17.1 §17.2 §17.3 §17.4 §17.6 §17.8 第 17 章 §22.1 §28.1 §28.6 §D.2

C

  1. Chen, Y., Benton, J., Radhakrishnan, A., Uesato, J., Denison, C., Schulman, J., … Perez, E. (2025). Reasoning Models Don't Always Say What They Think. arXiv. 预印本 第 19 章 §19.4 §19.6 §19.7 第 19 章
  2. Chen, Y.-H., Wen, J., and Kirchner, J. H. (2026). Automated Researchers Can Mitigate Well-Characterized Alignment Failures. Anthropic Alignment Science Blog. 非同行评审 §23.4 第 29 章 §29.3 §29.4 §29.5 第 29 章 §D.2
  3. Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., and Amodei, D. (2017). Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems. §6.3 §6.6 第 6 章
  4. Christiano, P., Shlegeris, B., and Amodei, D. (2018). Supervising strong learners by amplifying weak experts. arXiv. 预印本 §7.1 §14.3 第 14 章
  5. Christiano, P., Cotra, A., and Xu, M. (2021). Eliciting latent knowledge: How to tell if your eyes deceive you. Alignment Research Center. 非同行评审 §18.4 第 18 章
  6. Clymer, J., Gabrieli, N., Krueger, D., and Larsen, T. (2024). Safety Cases: How to Justify the Safety of Advanced AI Systems. arXiv. 预印本 §31.1 §31.4 第 31 章
  7. Cotra, A. (2018). Iterated Distillation and Amplification. AI Alignment Forum. 非同行评审 §14.3 第 14 章
  8. Cotra, A. (2021). The case for aligning narrowly superhuman models. AI Alignment Forum. 非同行评审 §11.1 第 11 章

D

  1. DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., … Zhang, Z. (2025). DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature. §6.3 §19.1 第 20 章 §20.1 §20.2 第 20 章 §22.1

F

  1. Farquhar, S., Varma, V., Kenton, Z., Gasteiger, J., Mikulik, V., and Shah, R. (2023). Challenges with unsupervised LLM knowledge discovery. arXiv. 预印本 第 18 章 §18.5 第 18 章 第 18 章

G

  1. Gao, L., Schulman, J., and Hilton, J. (2022). Scaling Laws for Reward Model Overoptimization. International Conference on Machine Learning, 2023. 第 23 章 §23.2 §23.5 第 23 章 §D.2
  2. Gema, A. P., Leang, J. O. J., Hong, G., Devoto, A., Mancino, A. C. M., Saxena, R., … Minervini, P. (2024). Are We Done with MMLU? 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). doi:10.18653/v1/2025.naacl-long.262. §11.4
  3. Goel, S., Strüber, J., Auzina, I. A., Chandra, K. K., Kumaraguru, P., Kiela, D., … Geiping, J. (2025). Great Models Think Alike and this Undermines AI Oversight. International Conference on Machine Learning. §11.3 第 12 章 §12.3 §12.4 第 12 章 第 17 章 §17.7 第 17 章 第 24 章 §24.2 §24.3 §24.4 第 24 章 §28.6
  4. Goldowsky-Dill, N., Chughtai, B., Heimersheim, S., and Hobbhahn, M. (2025). Detecting Strategic Deception with Linear Probes. International Conference on Machine Learning. §18.6 第 18 章
  5. Google (n.d.). Machine Learning Crash Course. Google for Developers. 非同行评审 §2.4 第 4 章
  6. Greenblatt, R., and Shlegeris, B. (2024). The case for ensuring that powerful AIs are controlled. LessWrong / AI Alignment Forum. 非同行评审 §7.7 §10.1 §10.2 §10.4 第 10 章 §26.1 §26.6 第 26 章
  7. Greenblatt, R., Shlegeris, B., Sachan, K., and Roger, F. (2023). AI Control: Improving Safety Despite Intentional Subversion. International Conference on Machine Learning, 2024. 第 26 章 §26.1 §26.2 §26.3 §26.5 §26.6 第 26 章 §D.2
  8. Greenblatt, R., Denison, C., Wright, B., Roger, F., MacDiarmid, M., Marks, S., … Hubinger, E. (2024). Alignment faking in large language models. arXiv. 预印本 第 25 章 §25.1 §25.4 第 25 章 第 25 章

H

  1. Hendrycks, D. (2024). Introduction to AI Safety, Ethics, and Society. CRC Press. 第 1 章 第 4 章 §8.1 §8.2 §8.6 第 8 章 §9.2 第 9 章 §30.2 第 30 章 §C.1
  2. Hubinger, E., van Merwijk, C., Mikulik, V., Skalse, J., and Garrabrant, S. (2019). Risks from Learned Optimization in Advanced Machine Learning Systems. arXiv. 预印本 §25.1 §25.6 第 25 章
  3. Hubinger, E., Schiefer, N., Denison, C., and Perez, E. (2023). Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research. AI Alignment Forum. 非同行评审 §25.2 第 25 章
  4. Hubinger, E., Denison, C., Mu, J., Lambert, M., Tong, M., MacDiarmid, M., … Perez, E. (2024). Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. arXiv. 预印本 第 25 章 §25.1 §25.2 §25.3 §25.5 §25.6 第 25 章

I

  1. Irving, G. (2025). Dodging systematic human errors in scalable oversight. AI Alignment Forum. 非同行评审 §15.11 §28.3 第 28 章
  2. Irving, G., Christiano, P., and Amodei, D. (2018). AI safety via debate. arXiv. 预印本 §7.1 §15.1 §15.2 §15.6 §15.7 §15.8 第 15 章

J

  1. Jones, E., Tong, M., Mu, J., Mahfoud, M., Leike, J., Grosse, R., … Sharma, M. (2025). Forecasting Rare Language Model Behaviors. arXiv. 预印本 §28.5 第 28 章

K

  1. Karpathy, A. (2023). Let's build GPT: from scratch, in code, spelled out. YouTube. 非同行评审 第 5 章
  2. Kenton, Z., Siegel, N., Kramár, J., Brown-Cohen, J., Albanie, S., Bulian, J., … Shah, R. (2024). On scalable oversight with weak LLMs judging strong LLMs. Advances in Neural Information Processing Systems. §11.3 第 15 章 §15.2 §15.3 §15.4 §15.5 第 15 章 §22.1 §28.2 第 28 章 §30.3
  3. Khan, A., Hughes, J., Valentine, D., Ruis, L., Sachan, K., Radhakrishnan, A., … Perez, E. (2024). Debating with More Persuasive LLMs Leads to More Truthful Answers. International Conference on Machine Learning. 第 15 章 §15.2 §15.3 §15.4 §15.5 第 15 章 第 15 章 §22.1 §28.2 §30.3 第 30 章
  4. Kim, H., Ryu, D., Yi, X., Yao, J., Lian, J., Huang, M., … Xie, X. (2024). The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment. arXiv. 预印本 §C.3
  5. Kim, E. M., Garg, A., Peng, K., and Garg, N. (2025). Correlated Errors in Large Language Models. International Conference on Machine Learning. §24.2
  6. Kirchner, J. H., Chen, Y., Edwards, H., Leike, J., McAleese, N., and Burda, Y. (2024). Prover-Verifier Games improve legibility of LLM outputs. arXiv. 预印本 第 19 章 §19.3 §19.5 第 19 章
  7. Korbak, T., Balesni, M., Barnes, E., Bengio, Y., Benton, J., Bloom, J., … Mikulik, V. (2025). Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety. arXiv. 预印本 第 19 章
  8. Krakovna, V., Uesato, J., Mikulik, V., Rahtz, M., Everitt, T., Kumar, R., … Legg, S. (2020). Specification gaming: the flip side of AI ingenuity. Google DeepMind blog. 非同行评审 §8.1 §8.2 第 8 章
  9. Kunin, D., Guo, J., Devlin, T. D., and Xiang, D. (n.d.). Seeing Theory: A visual introduction to probability and statistics. Brown University. 非同行评审 第 3 章
  10. Kutasov, J., Loughridge, C., Sun, Y., Sleight, H., Shlegeris, B., Tracy, T., and Benton, J. (2025). Evaluating Control Protocols for Untrusted AI Agents. arXiv. 预印本 §10.2 第 26 章 §26.3 §26.4 §26.5 §26.6 第 26 章 第 26 章 §28.2
  11. Kwa, T., West, B., Becker, J., Deng, A., Garcia, K., Hasin, M., … Chan, L. (2025). Measuring AI Ability to Complete Long Software Tasks. Advances in Neural Information Processing Systems 38. §1.4

L

  1. Lambert, N. (2025). Reinforcement Learning from Human Feedback. Manning Publications. 第 6 章
  2. Lambert, N., Castricato, L., von Werra, L., and Havrilla, A. (2022). Illustrating Reinforcement Learning from Human Feedback (RLHF). Hugging Face Blog. 非同行评审 第 6 章
  3. (2026a). Axioms. Lean Language Reference. 非同行评审 §20.1 第 20 章
  4. (2026b). Validating a Lean Proof. Lean Language Reference. 非同行评审 §20.6 第 20 章
  5. Lee, H., Phatale, S., Mansoor, H., Mesnard, T., Ferret, J., Lu, K., … Prakash, S. (2023). RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback. International Conference on Machine Learning, 2024. 第 21 章 §21.1 §21.2 §21.4 §21.6 第 21 章 §22.1
  6. Leike, J., Krueger, D., Everitt, T., Martic, M., Maini, V., and Legg, S. (2018). Scalable agent alignment via reward modeling: a research direction. arXiv. 预印本 §6.1 §7.1 §14.4 §14.6 第 14 章 §15.7
  7. Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., … Cobbe, K. (2023). Let's Verify Step by Step. International Conference on Learning Representations, 2024. 第 19 章 §19.1 §19.2 第 19 章 第 19 章 §22.1
  8. Liu, N. F., Zhang, T., and Liang, P. (2023). Evaluating Verifiability in Generative Search Engines. Findings of the Association for Computational Linguistics: EMNLP 2023. doi:10.18653/v1/2023.findings-emnlp.467. 第 20 章 §20.5 第 20 章 §22.1

M

  1. MacDiarmid, M., Wright, B., Uesato, J., Benton, J., Kutasov, J., Price, S., … Hubinger, E. (2025). Natural Emergent Misalignment from Reward Hacking in Production RL. arXiv. 预印本 §25.5
  2. Malan, D. J. (2022). CS50's Introduction to Programming with Python. Harvard University. 非同行评审 第 2 章
  3. Manheim, D., and Garrabrant, S. (2018). Categorizing Variants of Goodhart's Law. arXiv. 预印本 §8.6 第 8 章
  4. Marks, S., and Tegmark, M. (2023). The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets. Conference on Language Modeling, 2024. 第 18 章 §18.1 §18.2 §18.3 §18.4 §18.5 §18.6 第 18 章 第 18 章 §22.1
  5. Marks, S., Treutlein, J., Bricken, T., Lindsey, J., Marcus, J., Mishra-Sharma, S., … Hubinger, E. (2025). Auditing language models for hidden objectives. arXiv. 预印本 §10.2 第 27 章 §27.1 §27.2 §27.3 §27.4 §27.6 第 27 章
  6. McAleese, N., Pokorny, R. M., Uribe, J. F. C., Nitishinskaya, E., Trebacz, M., and Leike, J. (2024). LLM Critics Help Catch LLM Bugs. arXiv. 预印本 第 16 章 §16.3 §16.5 §16.7 第 16 章 第 16 章 §22.1 第 31 章
  7. Meta (2024a). Llama 3.1 Model Card. GitHub, meta-llama/llama-models. 非同行评审 §24.2
  8. Meta (2024b). Llama 3.2-Vision Model Card. GitHub, meta-llama/llama-models. 非同行评审 §24.2
  9. Michael, J., Mahdi, S., Rein, D., Petty, J., Dirani, J., Padmakumar, V., and Bowman, S. R. (2023). Debate Helps Supervise Unreliable Experts. arXiv. 预印本 第 15 章 §15.2 §15.3 §15.4 第 15 章 第 15 章 §22.1
  10. Miller, E. (2024). Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations. arXiv. 预印本 §3.3 §3.4 §3.5 第 3 章

N

  1. Needham, J., Edkins, G., Pimpale, G., Bartsch, H., and Hobbhahn, M. (2025). Large Language Models Often Know When They Are Being Evaluated. arXiv. 预印本 §25.1 §25.6
  2. NumPy Developers (2026). NumPy: the absolute basics for beginners. NumPy documentation. 非同行评审 §2.2 第 2 章

O

  1. OpenAI (2023). weak-to-strong. GitHub. 软件 第 17 章 §D.2
  2. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., … Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems. doi:10.52202/068431-2011. §1.4 §4.2 §4.4 §6.2 §6.3 §6.5 第 6 章 §13.6 §30.2 §D.2

P

  1. Pang, R. Y., Parrish, A., Joshi, N., Nangia, N., Phang, J., Chen, A., … Bowman, S. R. (2021). QuALITY: Question Answering with Long Input Texts, Yes! Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. §15.4 第 15 章
  2. Parasuraman, R., and Manzey, D. H. (2010). Complacency and Bias in Human Use of Automation: An Attentional Integration. Human Factors: The Journal of the Human Factors and Ergonomics Society. §13.2 §13.3 第 13 章
  3. Passi, S., and Vorvoreanu, M. (2022). Overreliance on AI: Literature Review. Microsoft. 非同行评审 第 13 章 §13.1 §13.2 §13.6 第 13 章
  4. Polak, B. (2007). Game Theory. Open Yale Courses. 非同行评审 第 15 章

R

  1. Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., and Finn, C. (2023). Direct Preference Optimization: Your Language Model is Secretly a Reward Model. Advances in Neural Information Processing Systems. doi:10.52202/075280-2338. §6.3 §6.4
  2. Recchia, G., Mangat, C. S., Nyachhyon, J., Sharma, M., Canavan, C., Epstein-Gross, D., and Abdulbari, M. (2025a). Confirmation Bias: A Challenge for Scalable Oversight. Proceedings of the AAAI Conference on Artificial Intelligence, 2026. doi:10.1609/aaai.v40i44.41124. §11.3 §11.5 §13.1 §13.2 §13.3 §13.4 §13.5 §13.6 第 13 章 §28.1 第 28 章 §D.2
  3. Recchia, G., Mangat, C. S., Li, I., and Krishnakumar, G. (2025b). FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research. Proceedings of the AAAI Conference on Artificial Intelligence, 2026. doi:10.1609/aaai.v40i44.41123. §16.6 第 16 章 第 16 章 §D.1 §D.2
  4. Recht, B., Roelofs, R., Schmidt, L., and Shankar, V. (2019). Do ImageNet Classifiers Generalize to ImageNet? International Conference on Machine Learning. §23.3
  5. Rein, D., Hou, B. L., Stickland, A. C., Petty, J., Pang, R. Y., Dirani, J., Michael, J., and Bowman, S. R. (2023). GPQA: A Graduate-Level Google-Proof Q&A Benchmark. Conference on Language Modeling, 2024. §11.4 §11.7 第 11 章
  6. Ren, R., Basart, S., Khoja, A., Gatti, A., Phan, L., Yin, X., … Hendrycks, D. (2024). Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? arXiv, v3 (a substantially different version appeared in the NeurIPS 2024 Datasets and Benchmarks Track). 预印本 §30.3 第 30 章 第 30 章 §D.2

S

  1. Sanderson, G. (2016). Essence of linear algebra. 3Blue1Brown (YouTube). 非同行评审 第 2 章
  2. Sanderson, G. (2017a). Essence of calculus. 3Blue1Brown (YouTube). 非同行评审 第 2 章
  3. Sanderson, G. (2017b). Neural networks. 3Blue1Brown (YouTube). 非同行评审 第 4 章
  4. Sanderson, G. (2024a). Large Language Models explained briefly. 3Blue1Brown. 非同行评审 第 5 章
  5. Sanderson, G. (2024b). Transformers, the tech behind LLMs. 3Blue1Brown. 非同行评审 §5.2 第 5 章
  6. Saunders, W., Yeh, C., Wu, J., Bills, S., Ouyang, L., Ward, J., and Leike, J. (2022). Self-critiquing models for assisting human evaluators. arXiv. 预印本 第 16 章 §16.1 §16.2 §16.3 §16.4 §16.5 第 16 章 第 16 章 §22.1 §30.3
  7. Schoen, B., Nitishinskaya, E., Balesni, M., Højmark, A., Hofstätter, F., Scheurer, J., … Hobbhahn, M. (2025). Stress Testing Deliberative Alignment for Anti-Scheming Training. arXiv. 预印本 §25.6 第 25 章
  8. Shah, R., Varma, V., Kumar, R., Phuong, M., Krakovna, V., Uesato, J., and Kenton, Z. (2022). Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals. arXiv. 预印本 §8.3 §8.4 §8.7 第 8 章 §10.4
  9. Shah, R., Farquhar, S., and Dragan, A. (2024). AGI Safety and Alignment at Google DeepMind: A Summary of Recent Work. GDM Alignment Research Blog. 非同行评审 §7.7 第 7 章
  10. Sharma, M., Tong, M., Korbak, T., Duvenaud, D., Askell, A., Bowman, S. R., … Perez, E. (2023). Towards Understanding Sycophancy in Language Models. International Conference on Learning Representations, 2024. §8.5 §8.7 第 8 章
  11. Sheshadri, A., Ewart, A., Fronsdal, K., Gupta, I., Bowman, S. R., Price, S., Marks, S., and Wang, R. (2026). AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors. arXiv. 预印本 第 27 章 §27.5 §27.6 第 27 章 §D.2
  12. Si, C., Hashimoto, T., and Yang, D. (2025). The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas. arXiv. 预印本 §29.1
  13. Sipser, M. (2013). Introduction to the Theory of Computation. Cengage. 第 15 章
  14. Sudhir, A. P., Kaunismaa, J., and Panickssery, A. (2025). A Benchmark for Scalable Oversight Protocols. arXiv. 预印本 §28.4 第 28 章 §30.3
  15. Sun, Z., Yu, L., Shen, Y., Liu, W., Yang, Y., Welleck, S., and Gan, C. (2024). Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision. Advances in Neural Information Processing Systems. 第 17 章 §17.4 第 17 章 §22.1

T

  1. Turpin, M., Michael, J., Perez, E., and Bowman, S. R. (2023). Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting. Advances in Neural Information Processing Systems. 第 19 章 §19.5 §19.6 第 19 章

V

  1. van der Weij, T., Hofstätter, F., Jaffe, O., Brown, S. F., and Ward, F. R. (2024). AI Sandbagging: Language Models can Strategically Underperform on Evaluations. International Conference on Learning Representations, 2025. §25.1 §25.6
  2. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems. §5.2 第 5 章

W

  1. Wen, J., Zhong, R., Khan, A., Perez, E., Steinhardt, J., Huang, M., … Feng, S. (2024). Language Models Learn to Mislead Humans via RLHF. International Conference on Learning Representations, 2025. §1.4 第 7 章 §9.2 §9.3 §9.4 第 9 章 第 9 章 §10.4 §30.1
  2. Wen, J., Ankner, Z., Somani, A., Hase, P., Marks, S., Goldman-Wetzler, J., … Leike, J. (2025). Unsupervised Elicitation of Language Models. arXiv. 预印本 第 17 章 §17.5 §17.6 第 17 章 §22.1 §D.2
  3. Wen, J., Qiu, L., Benton, J., Kirchner, J. H., and Leike, J. (2026). Automated Weak-to-Strong Researcher. Anthropic Alignment Science Blog. 非同行评审 第 29 章 §29.2 §29.4 第 29 章 §D.2
  4. Wolfe, J. M., Horowitz, T. S., and Kenner, N. M. (2005). Rare items often missed in visual searches. Nature. §13.3
  5. Wu, G., and Hilton, J. (2024). Estimating the Probabilities of Rare Outputs in Language Models. International Conference on Learning Representations, 2025. §28.5 第 28 章
  6. Wu, J., Ouyang, L., Ziegler, D. M., Stiennon, N., Lowe, R., Leike, J., and Christiano, P. (2021). Recursively Summarizing Books with Human Feedback. arXiv. 预印本 第 14 章 §14.1 §14.2 §14.5 §14.6 第 14 章 第 14 章 §22.1

Z

  1. Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., … Stoica, I. (2023). Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. Advances in Neural Information Processing Systems. doi:10.52202/075280-2020. §12.1 §12.2 §12.3 §12.4 §12.5 第 12 章 第 12 章 §13.1