Aligning AI With Shared Human Values

We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to filter out needlessly inflammatory chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete understanding of basic ethical knowledge. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.

AI Research Considerations for Human Existential Safety (ARCHES)

Framed in positive terms, this report examines how technical AI research might be steered in a manner that is more attentive to humanity's long-term prospects for survival as a species. In negative terms, we ask what existential risks humanity might face from AI development in the next century, and by what principles contemporary technical research might be directed to address those risks. A key property of hypothetical AI technologies is introduced, called \emph{prepotence}, which is useful for delineating a variety of potential existential risks from artificial intelligence, even as AI paradigms might shift. A set of \auxref{dirtot} contemporary research \directions are then examined for their potential benefit to existential safety. Each research direction is explained with a scenario-driven motivation, and examples of existing work from which to build. The research directions present their own risks and benefits to society that could occur at various scales of impact, and in particular are not guaranteed to benefit existential safety if major developments in them are deployed without adequate forethought and oversight. As such, each direction is accompanied by a consideration of potentially negative side effects.

Neural Networks are Surprisingly Modular

The learned weights of a neural network are often considered devoid of scrutable internal structure. In order to attempt to discern structure in these weights, we introduce a measurable notion of modularity for multi-layer perceptrons (MLPs), and investigate the modular structure of MLPs trained on datasets of small images. Our notion of modularity comes from the graph clustering literature: a "module" is a set of neurons with strong internal connectivity but weak external connectivity. We find that MLPs that undergo training and weight pruning are often significantly more modular than random networks with the same distribution of weights. Interestingly, they are much more modular when trained with dropout. Further analysis shows that this modularity seems to arise mostly for networks trained on learnable datasets. We also present exploratory analyses of the importance of different modules for performance and how modules depend on each other. Understanding the modular structure of neural networks, when such structure exists, will hopefully render their inner workings more interpretable to engineers.

Logical Induction

We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations, and its own probabilities. We show that our algorithm, an instance of what we call a logical inductor, satisfies a number of intuitive desiderata, including: (1) it learns to predict patterns of truth and falsehood in logical statements, often long before having the resources to evaluate the statements, so long as the patterns can be written down in polynomial time; (2) it learns to use appropriate statistical summaries to predict sequences of statements whose truth values appear pseudorandom; and (3) it learns to have accurate beliefs about its own current beliefs, in a manner that avoids the standard paradoxes of self-reference. For example, if a given computer program only ever produces outputs in a certain range, a logical inductor learns this fact in a timely manner; and if late digits in the decimal expansion of $\pi$ are difficult to predict, then a logical inductor learns to assign $\approx 10\%$ probability to "the $n$th digit of $\pi$ is a 7" for large $n$. Logical inductors also learn to trust their future beliefs more than their current beliefs, and their beliefs are coherent in the limit (whenever $\phi \implies \psi$, $\mathbb{P}_\infty(\phi) \le \mathbb{P}_\infty(\psi)$, and so on); and logical inductors strictly dominate the universal semimeasure in the limit. These properties and many others all follow from a single logical induction criterion, which is motivated by a series of stock trading analogies. Roughly speaking, each logical sentence $\phi$ is associated with a stock that is worth \$1 per share if [...]

Servant of Many Masters: Shifting priorities in Pareto-optimal sequential decision-making

It is often argued that an agent making decisions on behalf of two or more principals who have different utility functions should adopt a {\em Pareto-optimal} policy, i.e., a policy that cannot be improved upon for one agent without making sacrifices for another. A famous theorem of Harsanyi shows that, when the principals have a common prior on the outcome distributions of all policies, a Pareto-optimal policy for the agent is one that maximizes a fixed, weighted linear combination of the principals' utilities. In this paper, we show that Harsanyi's theorem does not hold for principals with different priors, and derive a more precise generalization which does hold, which constitutes our main result. In this more general case, the relative weight given to each principal's utility should evolve over time according to how well the agent's observations conform with that principal's prior. The result has implications for the design of contracts, treaties, joint ventures, and robots.

Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making

Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs. Concretely, consider two players with different beliefs and utility functions who may cooperate to build a machine that takes actions on their behalf. A representation is needed for how much the machine's policy will prioritize each player's interests over time. Assuming the players have reached common knowledge of their situation, this paper derives a recursion that any Pareto optimal policy must satisfy. Two qualitative observations can be made from the recursion: the machine must (1) use each player's own beliefs in evaluating how well an action will serve that player's utility function, and (2) shift the relative priority it assigns to each player's expected utilities over time, by a factor proportional to how well that player's beliefs predict the machine's inputs. Observation (2) represents a substantial divergence from na\"{i}ve linear utility aggregation (as in Harsanyi's utilitarian theorem, and existing MORL algorithms), which is shown here to be inadequate for Pareto optimal sequential decision-making on behalf of players with different beliefs.