SafetyAnalyst: Interpretable, transparent, and steerable LLM safety moderation

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.

Value Internalization: Learning and Generalizing from Social Reward

Social rewards shape human behavior. During development, a caregiver guides a learner's behavior towards culturally aligned goals and values. How do these behaviors persist and generalize when the caregiver is no longer present, and the learner must continue autonomously? Here, we propose a model of value internalization where social feedback trains an internal social reward (ISR) model that generates internal rewards when social rewards are unavailable. Through empirical simulations, we show that an ISR model prevents agents from unlearning socialized behaviors and enables generalization in out-of-distribution tasks. We characterize the implications of incomplete internalization, akin to "reward hacking" on the ISR. Additionally, we show that our model internalizes prosocial behavior in a multi-agent environment. Our work provides a foundation for understanding how humans acquire and generalize values and offers insights for aligning AI with human values.

Multilingual Trolley Problems for Language Models

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.

Cooperate or Collapse: Emergence of Sustainability Behaviors in a Society of LLM Agents

In the rapidly evolving field of artificial intelligence, ensuring safe decision-making of Large Language Models (LLMs) is a significant challenge. This paper introduces Governance of the Commons Simulation (GovSim), a simulation platform designed to study strategic interactions and cooperative decision-making in LLMs. Through this simulation environment, we explore the dynamics of resource sharing among AI agents, highlighting the importance of ethical considerations, strategic planning, and negotiation skills. GovSim is versatile and supports any text-based agent, including LLMs agents. Using the Generative Agent framework, we create a standard agent that facilitates the integration of different LLMs. Our findings reveal that within GovSim, only two out of 15 tested LLMs managed to achieve a sustainable outcome, indicating a significant gap in the ability of models to manage shared resources. Furthermore, we find that by removing the ability of agents to communicate, they overuse the shared resource, highlighting the importance of communication for cooperation. Interestingly, most LLMs lack the ability to make universalized hypotheses, which highlights a significant weakness in their reasoning skills. We open source the full suite of our research results, including the simulation environment, agent prompts, and a comprehensive web interface.

CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models

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 insight 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.

Learning to Coordinate with Humans using Action Features

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.

When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical 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.

Modeling Communication to Coordinate Perspectives in Cooperation

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.

Too many cooks: Coordinating multi-agent collaboration through inverse planning

Collaboration requires agents to coordinate their behavior on the fly, sometimes cooperating to solve a single task together and other times dividing it up into sub-tasks to work on in parallel. Underlying the human ability to collaborate is theory-of-mind, the ability to infer the hidden mental states that drive others to act. Here, we develop Bayesian Delegation, a decentralized multi-agent learning mechanism with these abilities. Bayesian Delegation enables agents to rapidly infer the hidden intentions of others by inverse planning. These inferences enable agents to flexibly decide in the absence of communication when to cooperate on the same sub-task and when to work on different sub-tasks in parallel. We test this model in a suite of multi-agent Markov decision processes inspired by cooking problems. To succeed, agents must coordinate both their high-level plans (e.g., what sub-task they should work on) and their low-level actions (e.g., avoiding collisions). Bayesian Delegation bridges these two levels and rapidly aligns agents' beliefs about who should work on what without any communication. When agents cooperate on the same sub-task, coordinated plans emerge that enable the group of agents to achieve tasks no agent can complete on their own. Our model outperforms lesioned agents without Bayesian Delegation or without the ability to cooperate on the same sub-task.

Finding Friend and Foe in Multi-Agent Games

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.