Alignment for Advanced Machine Learning Systems
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
This chapter surveys eight research areas organized around one question: As learning systems become increasingly intelligent and autonomous, what design principles can best ensure that their behavior is aligned with the interests of the operators? The chapter focuses on two major technical obstacles to AI alignment: the challenge of specifying the right kind of objective functions and the challenge of designing AI systems that avoid unintended consequences and undesirable behavior even in cases where the objective function does not line up perfectly with the intentions of the designers. The questions surveyed include the following: How can we train reinforcement learners to take actions that are more amenable to meaningful assessment by intelligent overseers? What kinds of objective functions incentivize a system to “not have an overly large impact” or “not have many side effects”? The chapter discusses these questions, related work, and potential directions for future research, with the goal of highlighting relevant research topics in machine learning that appear tractable today.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
Rational choice and the structure of the environment.
Simon, H. A. (1956) · Psychological Review · doi:10.1037/h0042769 · Cited by 5,919
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
Generative Adversarial Networks
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2661 · Cited by 4,477
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · cited 2×
“Generative models (as studied by, e.g., Gregor et al. [2015] and Lake, Salakhutdinov, and Tenenbaum [2015]) and imitation learning (e.g., Judah et al. [2014], Ross, Gordon, and Bagnell [2010], and Asfour et al. [2008]) are state-of-the-art when it comes to imitating the behavior of humans in…”
BackgroundMethodExplaining prediction models and individual predictions with feature contributions
Štrumbelj, E., & Kononenko, I. (2014) · Knowledge and Information Systems · doi:10.1007/s10115-013-0679-x · Cited by 2,286 · cited 1×
“In a related vein, Datta, Sen, and Zick (2016), ˇStrumbelj and Kononenko (2014), and Robnik-ˇSikonja and Kononenko (2008) define metrics for reporting the influence of various inputs and sets of inputs on the output of a black-box ML system.”
Background
Cited by
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Lehman, J., Clune, J., Misevic, D., Adami, C., Altenberg, L., Beaulieu, J., Bentley, P. J., Bernard, S., Beslon, G., Bryson, D. M., et al. (2020) · Artificial Life · doi:10.1162/artl_a_00319 · Cited by 181
Unsolved Problems in ML Safety
Hendrycks, D., Carlini, N., Schulman, J., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2109.13916 · Cited by 95
Advanced Artificial Agents Intervene in the Provision of Reward
Cohen, M. K., Hutter, M., & Osborne, M. A. (2022) · AI Magazine · doi:10.1002/aaai.12064 · Cited by 30
AI Research Considerations for Human Existential Safety (ARCHES)
Critch, A., & Krueger, D. (2020) · arXiv · doi:10.48550/arxiv.2006.04948 · Cited by 25
Self-citation
Metadata
- Authors
- Taylor, J., Yudkowsky, E., LaVictoire, P., & Critch, A.
- Venue
- Ethics of Artificial Intelligence
- Publisher
- Oxford University PressNew York
- Published
- 2020-09-17
- Pages
- 342-382
- OpenAlex
- W3093882308
- Cited by
- 59
- References
- 20
- FWCI
- 14.36
- Type
- book chapter
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Alignment for Advanced Machine Learning Systems. https://app.cochat.ai/papers/10.1093/oso/9780190905033.003.0013
- The paper
- Taylor, J., Yudkowsky, E., LaVictoire, P., & Critch, A. (2020). Alignment for Advanced Machine Learning Systems. Ethics of Artificial Intelligence. https://doi.org/10.1093/oso/9780190905033.003.0013
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.