Publications: Jared Kaplan
| Title | Year | Citations | Score |
|---|---|---|---|
|
Language models are few-shot learners
Advances in neural information processing systems 33, 1877-1901, 2020 View on Google Scholar ↗ |
2020 | 86560 | 100.0% |
|
Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray
Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford …, 2020 View on Google Scholar ↗ |
2020 | 14071 | 100.0% |
|
Scaling laws for neural language models
arXiv preprint arXiv:2001.08361, 2020 View on Google Scholar ↗ |
2020 | 10195 | 100.0% |
|
Language Models are Few-Shot Learners (GPT-3)
2026 View on Google Scholar ↗ |
2026 | 1889 | 100.0% |
|
Constitutional ai: Harmlessness from ai feedback
arXiv preprint arXiv:2212.08073, 2022 View on Google Scholar ↗ |
2022 | 5788 | 100.0% |
|
Evaluating large language models trained on code
arXiv preprint arXiv:2107.03374, 2021 View on Google Scholar ↗ |
2021 | 12730 | 100.0% |
|
Training a helpful and harmless assistant with reinforcement learning from human feedback
arXiv preprint arXiv:2204.05862, 2022 View on Google Scholar ↗ |
2022 | 4990 | 100.0% |
|
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
arXiv preprint arXiv:2206.04615, 2022 View on Google Scholar ↗ |
2022 | 3202 | 99.9% |
|
Language models (mostly) know what they know
arXiv preprint arXiv:2207.05221, 2022 View on Google Scholar ↗ |
2022 | 2362 | 99.9% |
|
Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models
arXiv preprint arXiv:2001.08361 1 (2), 3, 2020 View on Google Scholar ↗ |
2020 | 4278 | 99.9% |
|
In-context learning and induction heads
arXiv preprint arXiv:2209.11895, 2022 View on Google Scholar ↗ |
2022 | 1574 | 99.8% |
|
Discovering language model behaviors with model-written evaluations
Findings of the association for computational linguistics: ACL 2023, 13387-13434, 2023 View on Google Scholar ↗ |
2023 | 1494 | 99.8% |
|
Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned
arXiv preprint arXiv:2209.07858, 2022 View on Google Scholar ↗ |
2022 | 1445 | 99.8% |
|
A mathematical framework for transformer circuits
Transformer Circuits Thread 1 (1), 12, 2021 View on Google Scholar ↗ |
2021 | 1670 | 99.8% |
|
Toy models of superposition
arXiv preprint arXiv:2209.10652, 2022 View on Google Scholar ↗ |
2022 | 1113 | 99.7% |
|
Sleeper agents: Training deceptive llms that persist through safety training
arXiv preprint arXiv:2401.05566, 2024 View on Google Scholar ↗ |
2024 | 818 | 99.7% |
|
Measuring faithfulness in chain-of-thought reasoning
arXiv preprint arXiv:2307.13702, 2023 View on Google Scholar ↗ |
2023 | 972 | 99.7% |
|
Explaining neural scaling laws
Proceedings of the National Academy of Sciences 121 (27), e2311878121, 2024 View on Google Scholar ↗ |
2024 | 763 | 99.7% |
|
Reasoning models don't always say what they think
arXiv preprint arXiv:2505.05410, 2025 View on Google Scholar ↗ |
2025 | 642 | 99.7% |
|
Alignment faking in large language models
arXiv preprint arXiv:2412.14093 2 (1), 2024 View on Google Scholar ↗ |
2024 | 727 | 99.7% |
|
A general language assistant as a laboratory for alignment
arXiv preprint arXiv:2112.00861, 2021 View on Google Scholar ↗ |
2021 | 1073 | 99.6% |
|
Towards measuring the representation of subjective global opinions in language models
arXiv preprint arXiv:2306.16388, 2023 View on Google Scholar ↗ |
2023 | 608 | 99.6% |
|
Many-shot jailbreaking
Advances in Neural Information Processing Systems 37, 129696-129742, 2024 View on Google Scholar ↗ |
2024 | 532 | 99.5% |
|
Which economic tasks are performed with ai? evidence from millions of claude conversations
arXiv preprint arXiv:2503.04761, 2025 View on Google Scholar ↗ |
2025 | 333 | 99.5% |
|
Predictability and surprise in large generative models
Proceedings of the 2022 ACM conference on fairness, accountability, and …, 2022 View on Google Scholar ↗ |
2022 | 589 | 99.4% |
|
Studying large language model generalization with influence functions
arXiv preprint arXiv:2308.03296, 2023 View on Google Scholar ↗ |
2023 | 409 | 99.3% |
|
Sycophancy to subterfuge: Investigating reward-tampering in large language models
arXiv preprint arXiv:2406.10162, 2024 View on Google Scholar ↗ |
2024 | 308 | 99.2% |
|
Constitutional classifiers: Defending against universal jailbreaks across thousands of hours of red teaming
arXiv preprint arXiv:2501.18837, 2025 View on Google Scholar ↗ |
2025 | 239 | 99.2% |
|
The capacity for moral self-correction in large language models
arXiv preprint arXiv:2302.07459, 2023 View on Google Scholar ↗ |
2023 | 304 | 99.1% |
|
Scaling laws for autoregressive generative modeling
arXiv preprint arXiv:2010.14701, 2020 View on Google Scholar ↗ |
2020 | 781 | 99.0% |
|
Simplified models for LHC new physics searches
Journal of Physics G: Nuclear and Particle Physics 39 (10), 105005, 2012 View on Google Scholar ↗ |
2012 | 1556 | 99.0% |
|
Measuring progress on scalable oversight for large language models
arXiv preprint arXiv:2211.03540, 2022 View on Google Scholar ↗ |
2022 | 351 | 99.0% |
|
The effective field theory of inflation
Journal of High Energy Physics 2008 (03), 014-014, 2008 View on Google Scholar ↗ |
2008 | 1668 | 98.9% |
|
Evaluating and mitigating discrimination in language model decisions
arXiv preprint arXiv:2312.03689, 2023 View on Google Scholar ↗ |
2023 | 218 | 98.7% |
|
Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022
URL https://arxiv. org/abs/2204.05862, 2025 View on Google Scholar ↗ |
2025 | 146 | 98.6% |
|
Alignment faking in large language models, 2024
URL https://arxiv. org/abs/2412.14093, 2024 View on Google Scholar ↗ |
2024 | 161 | 98.5% |
|
Scaling laws for transfer
arXiv preprint arXiv:2102.01293, 2021 View on Google Scholar ↗ |
2021 | 397 | 98.5% |
|
Evaluating large language models trained on code. arXiv 2021
arXiv preprint arXiv:2107.03374 10, 2021 View on Google Scholar ↗ |
2021 | 380 | 98.4% |
|
Clio: Privacy-preserving insights into real-world ai use
arXiv preprint arXiv:2412.13678, 2024 View on Google Scholar ↗ |
2024 | 127 | 98.0% |
|
Simple probes can catch sleeper agents
Anthropic Research Updates, 2024 View on Google Scholar ↗ |
2024 | 125 | 97.9% |
|
Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv
arXiv preprint arXiv:2204.05862, 2022 View on Google Scholar ↗ |
2022 | 195 | 97.8% |
|
Constitutional classifiers++: Efficient production-grade defenses against universal jailbreaks
arXiv preprint arXiv:2601.04603, 2026 View on Google Scholar ↗ |
2026 | 58 | 97.3% |
|
The analytic bootstrap and AdS superhorizon locality
Journal of High Energy Physics 2013 (12), 1-35, 2013 View on Google Scholar ↗ |
2013 | 649 | 97.1% |
|
An empirical model of large-batch training
arXiv preprint arXiv:1812.06162, 2018 View on Google Scholar ↗ |
2018 | 498 | 97.1% |
|
Question decomposition improves the faithfulness of model-generated reasoning
arXiv preprint arXiv:2307.11768, 2023 View on Google Scholar ↗ |
2023 | 101 | 96.8% |
|
Sabotage evaluations for frontier models
arXiv preprint arXiv:2410.21514, 2024 View on Google Scholar ↗ |
2024 | 80 | 96.6% |
|
Scaling laws from the data manifold dimension
Journal of Machine Learning Research 23 (9), 1-34, 2022 View on Google Scholar ↗ |
2022 | 136 | 96.6% |
|
The sloan digital sky survey-II supernova survey: technical summary
The Astronomical Journal 135 (1), 338-347, 2008 View on Google Scholar ↗ |
2008 | 741 | 96.6% |
|
Universality of long-distance AdS physics from the CFT bootstrap
Journal of High Energy Physics 2014 (8), 1-65, 2014 View on Google Scholar ↗ |
2014 | 522 | 96.5% |
|
What is the simplest quantum field theory?
Journal of High Energy Physics 2010 (9), 16, 2010 View on Google Scholar ↗ |
2010 | 682 | 96.5% |
|
Constitutional ai: Harmlessness from ai feedback. arXiv 2022
arXiv preprint arXiv:2212.08073, 2022 View on Google Scholar ↗ |
2022 | 114 | 95.8% |
|
Language models (mostly) know what they know (2022)
URL https://arxiv. org/abs/2207.05221 5, 2023 View on Google Scholar ↗ |
2023 | 78 | 95.8% |
|
Alignment faking in large language models. arXiv
Ji, M. Liu, J. Dai, et al. BeaverTails: Towards improved safety alignment of …, 2024 View on Google Scholar ↗ |
2024 | 64 | 95.7% |
|
Searching for the Kaluza-Klein graviton in bulk RS models
Journal of High Energy Physics 2007 (09), 013-013, 2007 View on Google Scholar ↗ |
2007 | 622 | 95.6% |
|
Specific versus general principles for constitutional ai
arXiv preprint arXiv:2310.13798, 2023 View on Google Scholar ↗ |
2023 | 73 | 95.4% |
|
A duality for the S matrix
Journal of High Energy Physics 2010 (3), 1-70, 2010 View on Google Scholar ↗ |
2010 | 548 | 95.4% |
|
Scaling laws and interpretability of learning from repeated data
arXiv preprint arXiv:2205.10487, 2022 View on Google Scholar ↗ |
2022 | 102 | 95.2% |
|
Virasoro conformal blocks and thermality from classical background fields
Journal of High Energy Physics 2015 (11), 200, 2015 View on Google Scholar ↗ |
2015 | 368 | 94.8% |
|
Data and parameter scaling laws for neural machine translation
Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 View on Google Scholar ↗ |
2021 | 142 | 94.6% |
|
A natural language for AdS/CFT correlators
Journal of High Energy Physics 2011 (11), 1-55, 2011 View on Google Scholar ↗ |
2011 | 431 | 94.2% |
|
Unitarity and the Holographic S-matrix
Journal of High Energy Physics 2012 (10), 1-47, 2012 View on Google Scholar ↗ |
2012 | 366 | 93.6% |
|
On tree amplitudes in gauge theory and gravity
Journal of High Energy Physics 2008 (04), 076-076, 2008 View on Google Scholar ↗ |
2008 | 405 | 92.9% |
|
Larochelle H., Ranzato M., Hadsell R., Balcan MF, Lin H
Language models are few-shot learners. Advances in neural information …, 2020 View on Google Scholar ↗ |
2020 | 146 | 92.2% |
|
Discovering new light states at neutrino experiments
Physical Review D—Particles, Fields, Gravitation, and Cosmology 82 (11), 113008, 2010 View on Google Scholar ↗ |
2010 | 362 | 92.2% |
|
Forecasting rare language model behaviors
arXiv preprint arXiv:2502.16797, 2025 View on Google Scholar ↗ |
2025 | 32 | 91.8% |
|
On the consistency relation of the three-point function in single-field inflation
Journal of Cosmology and Astroparticle Physics 2008 (02), 021, 2008 View on Google Scholar ↗ |
2008 | 352 | 91.7% |
|
Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, David W
2021 View on Google Scholar ↗ |
2021 | 98 | 91.6% |
|
Analyticity and the Holographic S-matrix
Journal of High Energy Physics 2012 (10), 1-45, 2012 View on Google Scholar ↗ |
2012 | 274 | 90.9% |
|
Softmax linear units
Transformer Circuits Thread, 95, 2022 View on Google Scholar ↗ |
2022 | 54 | 89.9% |
|
Scaling laws for neural language models. arXiv 2020
arXiv preprint arXiv:2001.08361 10, 2001 View on Google Scholar ↗ |
2001 | 361 | 89.7% |
|
On information loss in AdS3/CFT2
Journal of High Energy Physics 2016 (5), 109, 2016 View on Google Scholar ↗ |
2016 | 178 | 89.0% |
|
A general language assistant as a laboratory for alignment. arXiv
arXiv preprint arXiv:2112.00861, 2021 View on Google Scholar ↗ |
2021 | 77 | 89.0% |
|
Evaluating large language models trained on code. CoRR abs/2107.03374 (2021)
arXiv preprint arXiv:2107.03374, 2021 View on Google Scholar ↗ |
2021 | 70 | 87.8% |
|
The S-matrix in twistor space
Journal of High Energy Physics 2010 (3), 1-48, 2010 View on Google Scholar ↗ |
2010 | 238 | 87.6% |
|
A neural scaling law from the dimension of the data manifold
arXiv preprint arXiv:2004.10802, 2020 View on Google Scholar ↗ |
2020 | 89 | 86.6% |
|
LHC predictions from a Tevatron anomaly in the top quark forward-backward asymmetry
Journal of High Energy Physics 2011 (3), 3, 2011 View on Google Scholar ↗ |
2011 | 176 | 84.1% |
|
Exact Virasoro blocks from Wilson lines and background-independent operators
Journal of High Energy Physics 2017 (7), 1-51, 2017 View on Google Scholar ↗ |
2017 | 117 | 84.0% |
|
Lectures on AdS/CFT from the bottom up
2016 View on Google Scholar ↗ |
2016 | 123 | 83.6% |
|
Heavy flavor simplified models at the LHC
Journal of High Energy Physics 2012 (1), 1-35, 2012 View on Google Scholar ↗ |
2012 | 155 | 83.1% |
|
AdS field theory from conformal field theory
Journal of High Energy Physics 2013 (2), 54, 2013 View on Google Scholar ↗ |
2013 | 146 | 83.1% |
|
Language models are few-shot learners. CoRR abs/2005.14165 (2020)
2005 View on Google Scholar ↗ |
2005 | 196 | 82.8% |
|
& Amodei, D.(2020)
Language models are few-shot learners 15, 1877-1901, 2005 View on Google Scholar ↗ |
2005 | 191 | 82.4% |
|
Conformal blocks beyond the semi-classical limit
Journal of High Energy Physics 2016 (5), 1-26, 2016 View on Google Scholar ↗ |
2016 | 112 | 82.0% |
|
teusz Litwin
M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A …, 2020 View on Google Scholar ↗ |
2020 | 64 | 81.3% |
|
Non-Fermi-liquid fixed point in a Wilsonian theory of quantum critical metals
Physical Review B—Condensed Matter and Materials Physics 88 (12), 125116, 2013 View on Google Scholar ↗ |
2013 | 126 | 80.4% |
|
Non-Fermi-liquid behavior of large- quantum critical metals
Physical Review B 89 (16), 165114, 2014 View on Google Scholar ↗ |
2014 | 114 | 79.7% |
|
Covariant approaches to superconformal blocks
Journal of High Energy Physics 2014 (8), 1-30, 2014 View on Google Scholar ↗ |
2014 | 113 | 79.5% |
|
A numerical approach to Virasoro blocks and the information paradox
Journal of High Energy Physics 2017 (9), 1-39, 2017 View on Google Scholar ↗ |
2017 | 90 | 79.3% |
|
On the late-time behavior of Virasoro blocks and a classification of semiclassical saddles
Journal of High Energy Physics 2017 (4), 1-47, 2017 View on Google Scholar ↗ |
2017 | 89 | 79.1% |
|
Hawking from Catalan
Journal of High Energy Physics 2016 (5), 1-26, 2016 View on Google Scholar ↗ |
2016 | 87 | 77.0% |
|
An exact operator that knows its location
Journal of High Energy Physics 2018 (2), 2018 View on Google Scholar ↗ |
2018 | 70 | 76.2% |
|
A quantum correction to chaos
Journal of High Energy Physics 2016 (5), 1-22, 2016 View on Google Scholar ↗ |
2016 | 78 | 74.6% |
|
Eikonalization of conformal blocks
Journal of High Energy Physics 2015 (9), 1-45, 2015 View on Google Scholar ↗ |
2015 | 84 | 74.5% |
|
Degenerate operators and the 1/c expansion: Lorentzian resummations, high order computations, and super-Virasoro blocks
Journal of High Energy Physics 2017 (3), 1-47, 2017 View on Google Scholar ↗ |
2017 | 72 | 74.5% |
|
Aptasensor-encapsulating semi-permeable proteinosomes for direct target detection in non-treated biofluids
Biosensors and Bioelectronics 251, 116062, 2024 View on Google Scholar ↗ |
2024 | 9 | 72.1% |
|
Scattering states in AdS/CFT
arXiv preprint arXiv:1104.2597, 2011 View on Google Scholar ↗ |
2011 | 92 | 71.7% |
|
Lightcone effective Hamiltonians and RG flows
Journal of High Energy Physics 2018 (8), 1-52, 2018 View on Google Scholar ↗ |
2018 | 48 | 67.5% |
|
On the origin of light dark matter species
arXiv preprint arXiv:1004.0691, 2010 View on Google Scholar ↗ |
2010 | 72 | 64.9% |
|
Closed strings and weak gravity from higher-spin causality
Journal of High Energy Physics 2021 (2), 145, 2021 View on Google Scholar ↗ |
2021 | 21 | 62.8% |
|
Language models are few-shot learners. arXiv. org
2005 View on Google Scholar ↗ |
2005 | 66 | 61.6% |
|
Evaluating large language models trained on code, 2021. doi: 10.48550
arXiv preprint arXiv.2107.03374 10, 2021 View on Google Scholar ↗ |
2021 | 20 | 61.5% |
|
& Agarwal, S.(2020). Language models are few-shot learners
arXiv preprint arXiv:2005.14165, 2005 View on Google Scholar ↗ |
2005 | 60 | 59.6% |
|
Unraveling : grassmannian kinematics
Journal of High Energy Physics 2010 (3), 1-34, 2010 View on Google Scholar ↗ |
2010 | 57 | 59.6% |
|
Rewon Child, et al. 2020. Language models are few-shot learners
Advances in neural information processing systems. https://doi. org/10.48550 …, 2005 View on Google Scholar ↗ |
2005 | 57 | 58.5% |
|
A species or weak-gravity bound for large N gauge theories coupled to gravity
Journal of High Energy Physics 2019 (11), 142, 2019 View on Google Scholar ↗ |
2019 | 28 | 57.7% |
|
Scaling laws for neural language models (arXiv: 2001.08361). arXiv
2001 View on Google Scholar ↗ |
2001 | 53 | 56.8% |
|
Notes on contemporary machine learning for physicists
Lecture Notes, Department of Physics and Astronomy, Johns Hopkins University …, 2022 View on Google Scholar ↗ |
2022 | 10 | 55.7% |
|
Causality constraints in large QCD coupled to gravity
Physical Review D 104 (6), L061901, 2021 View on Google Scholar ↗ |
2021 | 16 | 55.4% |
|
Conformal blocks in the large D limit
Journal of High Energy Physics 2013 (8), 1-14, 2013 View on Google Scholar ↗ |
2013 | 40 | 53.8% |
|
Intraperitoneal fluid therapy in cholera and non-cholera diarrhoea: with special emphasis on the treatment of infants and children
Bulletin of the World Health Organization 42 (6), 837, 1970 View on Google Scholar ↗ |
1970 | 18 | 53.7% |
|
Enhanced pairing of quantum critical metals near
Physical Review B 92 (4), 045118, 2015 View on Google Scholar ↗ |
2015 | 33 | 51.0% |
|
The AdS3 propagator and the fate of locality
Journal of High Energy Physics 2018 (4), 1-52, 2018 View on Google Scholar ↗ |
2018 | 22 | 47.3% |
|
Extracting data from behind horizons with the AdS/CFT correspondence
arXiv preprint hep-th/0402066, 2004 View on Google Scholar ↗ |
2004 | 27 | 43.5% |
|
The bulk-to-boundary propagator in black hole microstate backgrounds
Journal of High Energy Physics 2019 (6), 107, 2019 View on Google Scholar ↗ |
2019 | 16 | 43.3% |
|
AdS3 reconstruction with general gravitational dressings
Journal of High Energy Physics 2019 (7), 141, 2019 View on Google Scholar ↗ |
2019 | 16 | 43.3% |
|
Avoiding an empty universe in RS I models and large-N gauge theories
arXiv preprint hep-ph/0609012, 2006 View on Google Scholar ↗ |
2006 | 26 | 43.1% |
|
Dark matter generation and split supersymmetry
arXiv preprint hep-ph/0601262, 2006 View on Google Scholar ↗ |
2006 | 23 | 41.1% |
|
Explaining debugging strategies to end-user programmers
IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC 2007 …, 2007 View on Google Scholar ↗ |
2007 | 23 | 40.7% |
|
Language models are few-shot learners. CoRR, abs/2005.14165
2005 View on Google Scholar ↗ |
2005 | 20 | 39.0% |
|
Decoupling of high dimension operators from the low energy sector in holographic models
arXiv preprint arXiv:1304.3458, 2013 View on Google Scholar ↗ |
2013 | 19 | 37.6% |
|
Language models are few-shot learners. Advances in neural information processing systems
arXiv: 2005.14165, 33-901, 2005 View on Google Scholar ↗ |
2005 | 17 | 36.5% |
|
An effective theory for holographic RG flows
Journal of High Energy Physics 2015 (2), 1-38, 2015 View on Google Scholar ↗ |
2015 | 16 | 35.0% |
|
Language models are few-shot learners. OpenAI
2005 View on Google Scholar ↗ |
2005 | 13 | 32.7% |
|
others. Evaluating large language models trained on code
ACM Transactions on Software Engineering and Methodology 32 (3), 1-43, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Evaluating Large Language Models Trained on Code.(Jul. 2021)
URL http://arxiv. org/abs/2107.03374, 2021 View on Google Scholar ↗ |
2021 | 5 | 26.8% |
|
Explaining scaling laws of neural network generalization
2022 View on Google Scholar ↗ |
2022 | 3 | 26.5% |
|
A new theory of anyons
arXiv preprint arXiv:1205.6816, 2012 View on Google Scholar ↗ |
2012 | 8 | 24.1% |
|
Slow fermions in quantum critical metals
arXiv preprint arXiv:1402.5413, 2014 View on Google Scholar ↗ |
2014 | 7 | 22.3% |
|
Rewon Child, Aditya Ramesh, Daniel Ziegler, Je rey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Sco Gray
Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford …, 2020 View on Google Scholar ↗ |
2020 | 3 | 16.2% |
|
Qft lectures notes
Department of Physics and Astronomy, Johns Hopkins University, 2016 View on Google Scholar ↗ |
2016 | 3 | 13.6% |
|
Shyam p., Sastry G., Askell A
Language models are few-shot learners Advances in neural information …, 2020 View on Google Scholar ↗ |
2020 | 2 | 12.1% |
|
Explaining Neural Scaling Laws
2021 View on Google Scholar ↗ |
2021 | 1 | 8.0% |
|
The plasma puddle as a perturbative black hole
Journal of High Energy Physics 2007 (06), 024-024, 2007 View on Google Scholar ↗ |
2007 | 1 | 6.6% |