Fetching the paper…

Reading the bibliography…

2023

Specific versus General Principles for Constitutional AI

Kundu, Sandipan, Bai, Yuntao, Kadavath, Saurav et al.

Original
PDF
Post on X

Understand

Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-preservation or power.

Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles.
We find this approach effectively prevents the expression of such behaviors.
The success of simple principles motivates us to ask: can models learn general ethical behaviors from only a single written principle? To test this, we run experiments using a principle roughly stated as "do what's best for humanity".

Specific versus General Principles for Constitutional AI · Around

Built on

https://arxiv.org/abs/1910.10683
Original
C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-text transformer.” 2019 · 1910
Earlier work this paper cites.
P. Christiano, J. Leike, T. B. Brown, M. Martic, S. Legg, and D. Amodei, “Deep reinforcement learning from human preferences.” 2017
2017
Earlier work this paper cites.
Curran Associates, Inc., 2017
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. u. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems 30 · 2017
Earlier work this paper cites.
J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” CoRR
Original
2017
Earlier work this paper cites.
P. J. Liu, M. Saleh, E. Pot, B. Goodrich, R. Sepassi, L. Kaiser, and N. Shazeer, “Generating wikipedia by summarizing long sequences,” arXiv:1801.10198 [cs]
Original
2018
Earlier work this paper cites.
A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, “Improving language understanding by generative pre-training,” URL https://s3-us-west-2. amazonaws. com/openai-assets/research-covers/languageunsupervised/language understanding paper. pdf
2018
Earlier work this paper cites.
P. Christiano, B. Shlegeris, and D. Amodei, “Supervising strong learners by amplifying weak experts.” 2018
2018
Earlier work this paper cites.
G. Irving, P. Christiano, and D. Amodei, “Ai safety via debate.” 2018
2018
Earlier work this paper cites.
A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, “Language models are unsupervised multitask learners,” openai.com
2019
Earlier work this paper cites.
N. Stiennon, L. Ouyang, J. Wu, D. M. Ziegler, R. Lowe, C. Voss, A. Radford, D. Amodei, and P. Christiano, “Learning to summarize from human feedback.” 2020
2020
Earlier work this paper cites.
J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei, “Scaling laws for neural language models.” 2020
2020
Earlier work this paper cites.
T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, “Language models are few-shot learners.” 2020
2020
Earlier work this paper cites.
A. Askell, Y. Bai, A. Chen, D. Drain, D. Ganguli, T. Henighan, A. Jones, N. Joseph, B. Mann, N. DasSarma, N. Elhage, Z. Hatfield-Dodds, D. Hernandez, J. Kernion, K. Ndousse, C. Olsson, D. Amodei, T. Brown, J. Clark, S. McCandlish, C. Olah, and J. Kaplan, “A general language assistant as a laboratory for alignment.” 2021
2021
Earlier work this paper cites.

Similar

J. Wu, L. Ouyang, D. M. Ziegler, N. Stiennon, R. Lowe, J. Leike, and P. Christiano, “Recursively summarizing books with human feedback.” 2021
2021
Cited alongside, same era.
https://arxiv.org/abs/2106.01465
Original
J. Zhao, D. Khashabi, T. Khot, A. Sabharwal, and K.-W. Chang, “Ethical-advice taker: Do language models understand natural language interventions?” 2021 · 2021
Cited alongside, same era.
Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, Nov., 2021
T. Schick and H. Schütze, “Generating datasets with pretrained language models,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021
Cited alongside, same era.
https://arxiv.org/abs/2212.08073
Original
Y. Bai, S. Kadavath, S. Kundu, A. Askell, J. Kernion, A. Jones, A. Chen, A. Goldie, A. Mirhoseini, C. McKinnon, C. Chen, C. Olsson, C. Olah, D. Hernandez, D. Drain, D. Ganguli, D. Li, E. Tran-Johnson, E. Perez, J. Kerr, J. Mueller, J. Ladish, J. Landau, K. Ndousse, K. Lukosuite, L. Lovitt, M. Sellitto, N. Elhage, N. Schiefer, N. Mercado, N. DasSarma, R. Lasenby, R. Larson, S. Ringer, S. Johnston, S. Kravec, S. E. Showk, S. Fort, T. Lanham, T. Telleen-Lawton, T. Conerly, T. Henighan, T. Hume, S. R. Bowman, Z. Hatfield-Dodds, B. Mann, D. Amodei, N. Joseph, S. McCandlish, T. Brown, and J. Kaplan, “Constitutional ai: Harmlessness from ai feedback.” 2022 · 2022

Then

https://arxiv.org/abs/2210.15893
Original
W. Shi, E. Dinan, K. Shuster, J. Weston, and J. Xu, “When life gives you lemons, make cherryade: Converting feedback from bad responses into good labels.” 2022 · 2022
Later among the works it cites.
https://arxiv.org/abs/2210.11610
Original
J. Huang, S. S. Gu, L. Hou, Y. Wu, X. Wang, H. Yu, and J. Han, “Large language models can self-improve.” 2022 · 2022
Later among the works it cites.
https://arxiv.org/abs/2203.15556
Original
J. Hoffmann, S. Borgeaud, A. Mensch, E. Buchatskaya, T. Cai, E. Rutherford, D. d. L. Casas, L. A. Hendricks, J. Welbl, A. Clark, T. Hennigan, E. Noland, K. Millican, G. v. d. Driessche, B. Damoc, A. Guy, S. Osindero, K. Simonyan, E. Elsen, J. W. Rae, O. Vinyals, and L. Sifre, “Training compute-optimal large language models.” 2022 · 2022
Later among the works it cites.
May, 2022
T. Hartvigsen, S. Gabriel, H. Palangi, M. Sap, D. Ray, and E. Kamar, “Toxigen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection,” in ACL 2022 · 2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

https://arxiv.org/abs/2212.09251

E. Perez, S. Ringer, K. Lukosuite, K. Nguyen, E. Chen, S. Heiner, C. Pettit, C. Olsson, S. Kundu, S. Kadavath, A. Jones, A. Chen, B. Mann, B. Israel, B. Seethor, C. McKinnon, C. Olah, D. Yan, D. Amodei, D. Amodei, D. Drain, D. Li, E. Tran-Johnson, G. Khundadze, J. Kernion, J. Landis, J. Kerr, J. Mueller, J. Hyun, J. Landau, K. Ndousse, L. Goldberg, L. Lovitt, M. Lucas, M. Sellitto, M. Zhang, N. Kingsland, N. Elhage, N. Joseph, N. Mercado, N. DasSarma, O. Rausch, R. Larson, S. McCandlish, S. Johnston, S. Kravec, S. E. Showk, T. Lanham, T. Telleen-Lawton, T. Brown, T. Henighan, T. Hume, Y. Bai, Z. Hatfield-Dodds, J. Clark, S. R. Bowman, A. Askell, R. Grosse, D. Hernandez, D. Ganguli, E. Hubinger, N. Schiefer, and J. Kaplan, “Discovering language model behaviors with model-written evaluations.” 2022 · 2022

Cited alongside, same era.

Y. Bai, A. Jones, K. Ndousse, A. Askell, A. Chen, N. DasSarma, D. Drain, S. Fort, D. Ganguli, T. Henighan, N. Joseph, S. Kadavath, J. Kernion, T. Conerly, S. El-Showk, N. Elhage, Z. Hatfield-Dodds, D. Hernandez, T. Hume, S. Johnston, S. Kravec, L. Lovitt, N. Nanda, C. Olsson, D. Amodei, T. Brown, J. Clark, S. McCandlish, C. Olah, B. Mann, and J. Kaplan, “Training a helpful and harmless assistant with reinforcement learning from human feedback.” 2022

2022

Cited alongside, same era.

A. Power, Y. Burda, H. Edwards, I. Babuschkin, and V. Misra, “Grokking: Generalization beyond overfitting on small algorithmic datasets,” CoRR

2022

Cited alongside, same era.

https://arxiv.org/abs/2211.03540

S. R. Bowman, J. Hyun, E. Perez, E. Chen, C. Pettit, S. Heiner, K. Lukosuite, A. Askell, A. Jones, A. Chen, A. Goldie, A. Mirhoseini, C. McKinnon, C. Olah, D. Amodei, D. Amodei, D. Drain, D. Li, E. Tran-Johnson, J. Kernion, J. Kerr, J. Mueller, J. Ladish, J. Landau, K. Ndousse, L. Lovitt, N. Elhage, N. Schiefer, N. Joseph, N. Mercado, N. DasSarma, R. Larson, S. McCandlish, S. Kundu, S. Johnston, S. Kravec, S. E. Showk, S. Fort, T. Telleen-Lawton, T. Brown, T. Henighan, T. Hume, Y. Bai, Z. Hatfield-Dodds, B. Mann, and J. Kaplan, “Measuring progress on scalable oversight for large language models.” 2022 · 2022

Cited alongside, same era.

https://arxiv.org/abs/2206.05802

Original

W. Saunders, C. Yeh, J. Wu, S. Bills, L. Ouyang, J. Ward, and J. Leike, “Self-critiquing models for assisting human evaluators.” 2022 · 2022

Cited alongside, same era.

https://arxiv.org/abs/2209.07858

D. Ganguli, L. Lovitt, J. Kernion, A. Askell, Y. Bai, S. Kadavath, B. Mann, E. Perez, N. Schiefer, K. Ndousse, A. Jones, S. Bowman, A. Chen, T. Conerly, N. DasSarma, D. Drain, N. Elhage, S. El-Showk, S. Fort, Z. H. Dodds, T. Henighan, D. Hernandez, T. Hume, J. Jacobson, S. Johnston, S. Kravec, C. Olsson, S. Ringer, E. Tran-Johnson, D. Amodei, T. Brown, N. Joseph, S. McCandlish, C. Olah, J. Kaplan, and J. Clark, “Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned.” 2022 · 2022

Cited alongside, same era.

R. Thoppilan, D. D. Freitas, J. Hall, N. Shazeer, A. Kulshreshtha, H. Cheng, A. Jin, T. Bos, L. Baker, Y. Du, Y. Li, H. Lee, H. S. Zheng, A. Ghafouri, M. Menegali, Y. Huang, M. Krikun, D. Lepikhin, J. Qin, D. Chen, Y. Xu, Z. Chen, A. Roberts, M. Bosma, Y. Zhou, C. Chang, I. Krivokon, W. Rusch, M. Pickett, K. S. Meier-Hellstern, M. R. Morris, T. Doshi, R. D. Santos, T. Duke, J. Soraker, B. Zevenbergen, V. Prabhakaran, M. Diaz, B. Hutchinson, K. Olson, A. Molina, E. Hoffman-John, J. Lee, L. Aroyo, R. Rajakumar, A. Butryna, M. Lamm, V. Kuzmina, J. Fenton, A. Cohen, R. Bernstein, R. Kurzweil, B. Aguera-Arcas, C. Cui, M. Croak, E. Chi, and Q. Le, “Lamda: Language models for dialog applications,” CoRR

2022

Cited alongside, same era.

L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. L. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al

Original

2022

Cited alongside, same era.

https://arxiv.org/abs/2202.03286

Original

E. Perez, S. Huang, F. Song, T. Cai, R. Ring, J. Aslanides, A. Glaese, N. McAleese, and G. Irving, “Red teaming language models with language models.” 2022 · 2022

Later among the works it cites.

Association for Computational Linguistics, Gyeongju, Republic of Korea, Oct., 2022

Y.-J. Lee, C.-G. Lim, Y. Choi, J.-H. Lm, and H.-J. Choi, “PERSONACHATGEN: Generating personalized dialogues using GPT-3,” in Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge · 2022

Later among the works it cites.

Association for Computational Linguistics, Seattle, United States, July, 2022

P. West, C. Bhagavatula, J. Hessel, J. Hwang, L. Jiang, R. Le Bras, X. Lu, S. Welleck, and Y. Choi, “Symbolic knowledge distillation: from general language models to commonsense models,” in Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · 2022

Later among the works it cites.

https://arxiv.org/abs/2209.15189

C. Snell, D. Klein, and R. Zhong, “Learning by distilling context.” 2022 · 2022

Later among the works it cites.

https://arxiv.org/abs/2207.05221

S. Kadavath, T. Conerly, A. Askell, T. Henighan, D. Drain, E. Perez, N. Schiefer, Z. H. Dodds, N. DasSarma, E. Tran-Johnson, S. Johnston, S. El-Showk, A. Jones, N. Elhage, T. Hume, A. Chen, Y. Bai, S. Bowman, S. Fort, D. Ganguli, D. Hernandez, J. Jacobson, J. Kernion, S. Kravec, L. Lovitt, K. Ndousse, C. Olsson, S. Ringer, D. Amodei, T. Brown, J. Clark, N. Joseph, B. Mann, S. McCandlish, C. Olah, and J. Kaplan, “Language models (mostly) know what they know.” 2022 · 2022

Later among the works it cites.

https://arxiv.org/abs/2204.02311

A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, P. Barham, H. W. Chung, C. Sutton, S. Gehrmann, P. Schuh, K. Shi, S. Tsvyashchenko, J. Maynez, A. Rao, P. Barnes, Y. Tay, N. Shazeer, V. Prabhakaran, E. Reif, N. Du, B. Hutchinson, R. Pope, J. Bradbury, J. Austin, M. Isard, G. Gur-Ari, P. Yin, T. Duke, A. Levskaya, S. Ghemawat, S. Dev, H. Michalewski, X. Garcia, V. Misra, K. Robinson, L. Fedus, D. Zhou, D. Ippolito, D. Luan, H. Lim, B. Zoph, A. Spiridonov, R. Sepassi, D. Dohan, S. Agrawal, M. Omernick, A. M. Dai, T. S. Pillai, M. Pellat, A. Lewkowycz, E. Moreira, R. Child, O. Polozov, K. Lee, Z. Zhou, X. Wang, B. Saeta, M. Diaz, O. Firat, M. Catasta, J. Wei, K. Meier-Hellstern, D. Eck, J. Dean, S. Petrov, and N. Fiedel, “Palm: Scaling language modeling with pathways.” 2022 · 2022

Later among the works it cites.

https://arxiv.org/abs/2302.07459

D. Ganguli, A. Askell, N. Schiefer, T. I. Liao, K. Lukosuite, A. Chen, A. Goldie, A. Mirhoseini, C. Olsson, D. Hernandez, D. Drain, D. Li, E. Tran-Johnson, E. Perez, J. Kernion, J. Kerr, J. Mueller, J. Landau, K. Ndousse, K. Nguyen, L. Lovitt, M. Sellitto, N. Elhage, N. Mercado, N. DasSarma, O. Rausch, R. Lasenby, R. Larson, S. Ringer, S. Kundu, S. Kadavath, S. Johnston, S. Kravec, S. E. Showk, T. Lanham, T. Telleen-Lawton, T. Henighan, T. Hume, Y. Bai, Z. Hatfield-Dodds, B. Mann, D. Amodei, N. Joseph, S. McCandlish, T. Brown, C. Olah, J. Clark, S. R. Bowman, and J. Kaplan, “The capacity for moral self-correction in large language models.” 2023 · 2023

Closest in time.

Z. Sun, Y. Shen, Q. Zhou, H. Zhang, Z. Chen, D. Cox, Y. Yang, and C. Gan, “Principle-driven self-alignment of language models from scratch with minimal human supervision.” 2023

2023

Closest in time.