Publications: Paul Christiano
Download CSV for Paul Christiano
| Title | Year | Citations | Score |
|---|---|---|---|
|
Training language models to follow instructions with human feedback
Advances in neural information processing systems 35, 27730-27744, 2022 View on Google Scholar ↗ |
2022 | 34368 | 100.0% |
|
Deep reinforcement learning from human preferences
Advances in neural information processing systems 30, 2017 View on Google Scholar ↗ |
2017 | 9186 | 99.9% |
|
Learning to summarize with human feedback
Advances in neural information processing systems 33, 3008-3021, 2020 View on Google Scholar ↗ |
2020 | 4523 | 99.9% |
|
Fine-tuning language models from human preferences
arXiv preprint arXiv:1909.08593, 2019 View on Google Scholar ↗ |
2019 | 3724 | 99.9% |
|
Concrete problems in AI safety
arXiv preprint arXiv:1606.06565, 2016 View on Google Scholar ↗ |
2016 | 6767 | 99.8% |
|
Sleeper agents: Training deceptive llms that persist through safety training
arXiv preprint arXiv:2401.05566, 2024 View on Google Scholar ↗ |
2024 | 834 | 99.7% |
|
Model evaluation for extreme risks
arXiv preprint arXiv:2305.15324, 2023 View on Google Scholar ↗ |
2023 | 379 | 99.3% |
|
Theano: A Python framework for fast computation of mathematical expressions
arXiv preprint arXiv:1605.02688, 2016 View on Google Scholar ↗ |
2016 | 1258 | 99.0% |
|
Recursively summarizing books with human feedback
arXiv preprint arXiv:2109.10862, 2021 View on Google Scholar ↗ |
2021 | 450 | 98.7% |
|
AI safety via debate
arXiv preprint arXiv:1805.00899, 2018 View on Google Scholar ↗ |
2018 | 770 | 98.3% |
|
A cryptographic test of quantumness and certifiable randomness from a single quantum device
Journal of the ACM (JACM) 68 (5), 1-47, 2021 View on Google Scholar ↗ |
2021 | 284 | 97.7% |
|
A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models
arXiv preprint arXiv:1611.03852, 2016 View on Google Scholar ↗ |
2016 | 533 | 96.9% |
|
Evaluating language-model agents on realistic autonomous tasks
arXiv preprint arXiv:2312.11671, 2023 View on Google Scholar ↗ |
2023 | 95 | 96.6% |
|
International scientific report on the safety of advanced ai (interim report)
arXiv preprint arXiv:2412.05282, 2024 View on Google Scholar ↗ |
2024 | 70 | 96.1% |
|
Electrical flows, laplacian systems, and faster approximation of maximum flow in undirected graphs
Proceedings of the forty-third annual ACM symposium on Theory of computing …, 2011 View on Google Scholar ↗ |
2011 | 478 | 94.9% |
|
Transfer from simulation to real world through learning deep inverse dynamics model
arXiv preprint arXiv:1610.03518, 2016 View on Google Scholar ↗ |
2016 | 334 | 94.6% |
|
Supervising strong learners by amplifying weak experts
arXiv preprint arXiv:1810.08575, 2018 View on Google Scholar ↗ |
2018 | 244 | 93.3% |
|
Quantum money from hidden subspaces
Proceedings of the forty-fourth annual ACM symposium on Theory of computing …, 2012 View on Google Scholar ↗ |
2012 | 328 | 92.6% |
|
Training language models to follow instructions with human feedback. arXiv. 2022. DOI: 10.48550
arXiv preprint arXiv.2203.02155 2, 2022 View on Google Scholar ↗ |
2022 | 67 | 92.1% |
|
& Lowe, R.(2022)
Training language models to follow instructions with human feedback 5, 88, 2022 View on Google Scholar ↗ |
2022 | 60 | 91.1% |
|
Unrestricted adversarial examples
arXiv preprint arXiv:1809.08352, 2018 View on Google Scholar ↗ |
2018 | 133 | 87.0% |
|
Backdoor defense, learnability and obfuscation
arXiv preprint arXiv:2409.03077, 2024 View on Google Scholar ↗ |
2024 | 12 | 78.0% |
|
Robust cooperation in the prisoner's dilemma: Program equilibrium via provability logic
arXiv preprint arXiv:1401.5577, 2014 View on Google Scholar ↗ |
2014 | 71 | 69.1% |
|
Deep reinforcement learning from human preferences. arXiv
arXiv preprint arXiv:1706.03741, 2017 View on Google Scholar ↗ |
2017 | 51 | 66.1% |
|
Estimating the expected output of wide random MLPs more efficiently than sampling
arXiv preprint arXiv:2605.05179, 2026 View on Google Scholar ↗ |
2026 | 3 | 61.0% |
|
Formalizing the presumption of independence
arXiv preprint arXiv:2211.06738, 2022 View on Google Scholar ↗ |
2022 | 10 | 55.7% |
|
Reflective oracles: A foundation for game theory in artificial intelligence
International Workshop on Logic, Rationality and Interaction, 411-415, 2015 View on Google Scholar ↗ |
2015 | 28 | 47.0% |
|
Online local learning via semidefinite programming
Proceedings of the forty-sixth annual ACM symposium on Theory of computing …, 2014 View on Google Scholar ↗ |
2014 | 20 | 38.9% |
|
Non-omniscience, probabilistic inference, and metamathematics
Machine Intelligence Research Institute, Berkeley, CA, June, 2014 View on Google Scholar ↗ |
2014 | 14 | 32.4% |
|
Lossless fault-tolerant data structures with additive overhead
Workshop on Algorithms and Data Structures, 243-254, 2011 View on Google Scholar ↗ |
2011 | 8 | 24.9% |
|
Provably manipulation-resistant reputation systems
Conference on Learning Theory, 670-697, 2016 View on Google Scholar ↗ |
2016 | 7 | 22.8% |
|
Towards a law of iterated expectations for heuristic estimators
arXiv preprint arXiv:2410.01290, 2024 View on Google Scholar ↗ |
2024 | 1 | 22.3% |
|
Manipulation-resistant online learning
UC Berkeley, 2017 View on Google Scholar ↗ |
2017 | 2 | 11.1% |
|
Open problem: Online local learning
Conference on Learning Theory, 1290-1294, 2014 View on Google Scholar ↗ |
2014 | 2 | 10.6% |