The ideal LLM content moderation system would be both structurally interpretable (so its decisions can be explained to users) and steerable (to reflect a community's values or align to safety standards). However, current systems fall short on both of these dimensions. To address this gap, we present SafetyAnalyst, a novel LLM safety moderation framework. Given a prompt, SafetyAnalyst creates a structured "harm-benefit tree," which identifies 1) the actions that could be taken if a compliant response were provided, 2) the harmful and beneficial effects of those actions (along with their likelihood, severity, and immediacy), and 3) the stakeholders that would be impacted by those effects. It then aggregates this structured representation into a harmfulness score based on a parameterized set of safety preferences, which can be transparently aligned to particular values. Using extensive harm-benefit features generated by SOTA LLMs on 19k prompts, we fine-tuned an open-weight LM to specialize in generating harm-benefit trees through symbolic knowledge distillation. On a comprehensive set of prompt safety benchmarks, we show that our system (average F1=0.75) outperforms existing LLM safety moderation systems (average F1$<$0.72) on prompt harmfulness classification, while offering the additional advantages of interpretability and steerability.

As AI systems pervade human life, ensuring that large language models (LLMs) make safe decisions remains a significant challenge. We introduce the Governance of the Commons Simulation (GovSim), a generative simulation platform designed to study strategic interactions and cooperative decision-making in LLMs. In GovSim, a society of AI agents must collectively balance exploiting a common resource with sustaining it for future use. This environment enables the study of how ethical considerations, strategic planning, and negotiation skills impact cooperative outcomes. We develop an LLM-based agent architecture and test it with the leading open and closed LLMs. We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%. Ablations reveal that successful multi-agent communication between agents is critical for achieving cooperation in these cases. Furthermore, our analyses show that the failure to achieve sustainable cooperation in most LLMs stems from their inability to formulate and analyze hypotheses about the long-term effects of their actions on the equilibrium of the group. Finally, we show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability. Taken together, GovSim enables us to study the mechanisms that underlie sustainable self-government with specificity and scale. We open source the full suite of our research results, including the simulation environment, agent prompts, and a comprehensive web interface.

As large language models (LLMs) are deployed in more and more real-world situations, it is crucial to understand their decision-making when faced with moral dilemmas. Inspired by a large-scale cross-cultural study of human moral preferences, "The Moral Machine Experiment", we set up the same set of moral choices for LLMs. We translate 1K vignettes of moral dilemmas, parametrically varied across key axes, into 100+ languages, and reveal the preferences of LLMs in each of these languages. We then compare the responses of LLMs to that of human speakers of those languages, harnessing a dataset of 40 million human moral judgments. We discover that LLMs are more aligned with human preferences in languages such as English, Korean, Hungarian, and Chinese, but less aligned in languages such as Hindi and Somali (in Africa). Moreover, we characterize the explanations LLMs give for their moral choices and find that fairness is the most dominant supporting reason behind GPT-4's decisions and utilitarianism by GPT-3. We also discover "language inequality" (which we define as the model's different development levels in different languages) in a series of meta-properties of moral decision making.

The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason about causality. Much of the existing work in natural language processing (NLP) focuses on evaluating commonsense causal reasoning in LLMs, thus failing to assess whether a model can perform causal inference in accordance with a set of well-defined formal rules. To address this, we propose a new NLP task, causal inference in natural language, inspired by the "causal inference engine" postulated by Judea Pearl et al. We compose a large dataset, CLadder, with 10K samples: based on a collection of causal graphs and queries (associational, interventional, and counterfactual), we obtain symbolic questions and ground-truth answers, through an oracle causal inference engine. These are then translated into natural language. We evaluate multiple LLMs on our dataset, and we introduce and evaluate a bespoke chain-of-thought prompting strategy, CausalCoT. We show that our task is highly challenging for LLMs, and we conduct an in-depth analysis to gain deeper insights into the causal reasoning abilities of LLMs. Our data is open-sourced at https://huggingface.co/datasets/causalNLP/cladder, and our code can be found at https://github.com/causalNLP/cladder.

An unaddressed challenge in human-AI coordination is to enable AI agents to exploit the semantic relationships between the features of actions and the features of observations. Humans take advantage of these relationships in highly intuitive ways. For instance, in the absence of a shared language, we might point to the object we desire or hold up our fingers to indicate how many objects we want. To address this challenge, we investigate the effect of network architecture on the propensity of learning algorithms to exploit these semantic relationships. Across a procedurally generated coordination task, we find that attention-based architectures that jointly process a featurized representation of observations and actions have a better inductive bias for zero-shot coordination. Through fine-grained evaluation and scenario analysis, we show that the resulting policies are human-interpretable. Moreover, such agents coordinate with people without training on any human data.

One of the most remarkable things about the human moral mind is its flexibility. We can make moral judgments about cases we have never seen before. We can decide that pre-established rules should be broken. We can invent novel rules on the fly. Capturing this flexibility is one of the central challenges in developing AI systems that can interpret and produce human-like moral judgment. This paper details the results of a study of real-world decision makers who judge whether it is acceptable to break a well-established norm: ``no cutting in line.'' We gather data on how human participants judge the acceptability of line-cutting in a range of scenarios. Then, in order to effectively embed these reasoning capabilities into a machine, we propose a method for modeling them using a preference-based structure, which captures a novel modification to standard ``dual process'' theories of moral judgment.

Communication is highly overloaded. Despite this, even young children are good at leveraging context to understand ambiguous signals. We propose a computational account of overloaded signaling from a shared agency perspective which we call the Imagined We for Communication. Under this framework, communication helps cooperators coordinate their perspectives, allowing them to act together to achieve shared goals. We assume agents are rational cooperators, which puts constraints on how signals can be sent and interpreted. We implement this model in a set of simulations demonstrating this model's success under increasing ambiguity as well as increasing layers of reasoning. Our model is capable of improving performance with deeper recursive reasoning; however, it outperforms comparison baselines at even the shallowest level, highlighting how shared knowledge and cooperative logic can do much of the heavy-lifting in language.

Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these games address the real-life challenge of cooperation in the presence of unknown and uncertain teammates. This challenge is a key game mechanism in hidden role games. Here we develop the DeepRole algorithm, a multi-agent reinforcement learning agent that we test on The Resistance: Avalon, the most popular hidden role game. DeepRole combines counterfactual regret minimization (CFR) with deep value networks trained through self-play. Our algorithm integrates deductive reasoning into vector-form CFR to reason about joint beliefs and deduce partially observable actions. We augment deep value networks with constraints that yield interpretable representations of win probabilities. These innovations enable DeepRole to scale to the full Avalon game. Empirical game-theoretic methods show that DeepRole outperforms other hand-crafted and learned agents in five-player Avalon. DeepRole played with and against human players on the web in hybrid human-agent teams. We find that DeepRole outperforms human players as both a cooperator and a competitor.

Human social behavior is structured by relationships. We form teams, groups, tribes, and alliances at all scales of human life. These structures guide multi-agent cooperation and competition, but when we observe others these underlying relationships are typically unobservable and hence must be inferred. Humans make these inferences intuitively and flexibly, often making rapid generalizations about the latent relationships that underlie behavior from just sparse and noisy observations. Rapid and accurate inferences are important for determining who to cooperate with, who to compete with, and how to cooperate in order to compete. Towards the goal of building machine-learning algorithms with human-like social intelligence, we develop a generative model of multi-agent action understanding based on a novel representation for these latent relationships called Composable Team Hierarchies (CTH). This representation is grounded in the formalism of stochastic games and multi-agent reinforcement learning. We use CTH as a target for Bayesian inference yielding a new algorithm for understanding behavior in groups that can both infer hidden relationships as well as predict future actions for multiple agents interacting together. Our algorithm rapidly recovers an underlying causal model of how agents relate in spatial stochastic games from just a few observations. The patterns of inference made by this algorithm closely correspond with human judgments and the algorithm makes the same rapid generalizations that people do.

Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between goal and state. We show how to stochastically optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning. Finally, we demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games.