Max Kleiman‐Weiner

Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti et al.

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. This dataset enables the assessment of LLMs' decision-making processes in diverse linguistic contexts. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions: species, gender, fitness, status, age, and the number of lives involved. By correlating these preferences with the demographic distribution of language speakers and examining the consistency of LLM responses to various prompt paraphrasings, our findings provide insights into cross-lingual and ethical biases of LLMs and their intersection. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems and highlighting the importance of incorporating diverse perspectives in AI ethics. The results underscore the need for further research on the integration of multilingual dimensions in responsible AI research to ensure fair and equitable AI interactions worldwide. Our code and data are at https://github.com/causalNLP/moralmachine

Giorgio Piatti, Zhijing Jin, Max Kleiman-Weiner et al.

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.

Mehrzad Khosravi, Max Kleiman-Weiner, Hema Yoganarasimhan

Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming: consumers update beliefs from feedback and use those beliefs to guide future choices. In many markets, however, learning does not restart when consumers enter a new context: prior experience with a brand, product, or provider can shape beliefs in later, related decisions. We study this cross-context knowledge transfer, or meta-learning, in sequential choice. We design a hierarchical laboratory task in which participants repeatedly choose among airlines across routes and observe noisy binary outcomes. Reduced-form evidence shows that participants improve not only within routes, but also across routes: they choose better airlines earlier in later routes and reduce pseudo-regret. To identify the mechanism behind this transfer, we compare human choices to a no-transfer benchmark and a fully integrated Bayesian meta-learning benchmark. In particular, we introduce a class of boundedly rational meta dynamic programming policies, BRMDP(D), that approximate full integration using a limited number of hyper-posterior draws, denoted by D. Trial-by-trial likelihood comparisons show that low-D boundedly rational meta-learning, especially BRMDP(1), fits participant behavior better than both no transfer and fully integrated Bayesian transfer. Consumers, therefore, transfer brand-level regularities across contexts, but through coarse representations of prior uncertainty. The findings imply that models of consumer learning should allow for approximate cross-context transfer, and that managerial counterfactuals based on either no-transfer or fully integrated learning can be misleading.

Claire Yang, Maya Cakmak, Max Kleiman-Weiner

Empowerment, a measure of an agent's ability to control its environment, has been proposed as a universal goal-agnostic objective for motivating assistive behavior in AI agents. While multi-human settings like homes and hospitals are promising for AI assistance, prior work on empowerment-based assistance assumes that the agent assists one human in isolation. We introduce an open source multi-human gridworld test suite Disempower-Grid. Using Disempower-Grid, we empirically show that assistive RL agents optimizing for one human's empowerment can significantly reduce another human's environmental influence and rewards - a phenomenon we formalize as disempowerment. We characterize when disempowerment occurs in these environments and show that joint empowerment mitigates disempowerment at the cost of the user's reward. Our work reveals a broader challenge for the AI alignment community: goal-agnostic objectives that seem aligned in single-agent settings can become misaligned in multi-agent contexts.

Frieda Rong, Max Kleiman-Weiner

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.

Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner et al. · allen-ai, cmu

The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on. To address this gap, we present SafetyAnalyst, a novel AI safety moderation framework. Given an AI behavior, SafetyAnalyst uses chain-of-thought reasoning to analyze its potential consequences by creating a structured "harm-benefit tree," which enumerates harmful and beneficial actions and effects the AI behavior may lead to, along with likelihood, severity, and immediacy labels that describe potential impacts on stakeholders. SafetyAnalyst then aggregates all effects into a harmfulness score using 28 fully interpretable weight parameters, which can be aligned to particular safety preferences. We applied this framework to develop an open-source LLM prompt safety classification system, distilled from 18.5 million harm-benefit features generated by frontier LLMs on 19k prompts. On comprehensive benchmarks, we show that SafetyAnalyst (average F1=0.81) outperforms existing moderation systems (average F1$<$0.72) on prompt safety classification, while offering the additional advantages of interpretability, transparency, and steerability.

Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita et al.

As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has mainly examined the moral judgments in large language models (LLMs), rather than their underlying moral reasoning process. In contrast, we focus on a large-scale analysis of the moral reasoning traces provided by LLMs. Furthermore, unlike prior work that attempted to draw inferences from only a handful of moral dilemmas, our study leverages over 600 distinct trolley problems as probes for revealing the reasoning patterns that emerge within different LLMs. We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology. Our analysis reveals that LLM chains-of-thought tend to favor deontological principles based on moral obligations, while post-hoc explanations shift notably toward consequentialist rationales that emphasize utility. Our framework provides a foundation for understanding how LLMs process and articulate ethical considerations, an important step toward safe and interpretable deployment of LLMs in high-stakes decision-making environments. Our code is available at https://github.com/keenansamway/moral-lens .

Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang et al.

Large language models solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning computational constraints, meta-cognitive controls, knowledge representations, and transformation operations, then analyze their behavioral manifestations in reasoning traces. We propose a fine-grained cognitive evaluation framework and conduct the first large-scale analysis of 170K traces from 17 models across text, vision, and audio modalities, alongside 54 human think-aloud traces, which we make publicly available. Our analysis reveals systematic structural differences: humans employ hierarchical nesting and meta-cognitive monitoring while models rely on shallow forward chaining, with divergence most pronounced on ill-structured problems. Meta-analysis of 1,598 LLM reasoning papers reveals the research community concentrates on easily quantifiable behaviors (sequential organization: 55%, decomposition: 60%) while neglecting meta-cognitive controls (self-awareness: 16%, evaluation: 8%) that correlate with success. Models possess behavioral repertoires associated with success but fail to deploy them spontaneously. Leveraging these patterns, we develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 60% on complex problems. By bridging cognitive science and LLM research, we establish a foundation for developing models that reason through principled cognitive mechanisms rather than brittle spurious reasoning shortcuts or memorization, opening new directions for both improving model capabilities and testing theories of human cognition at scale.

Mingwei Ma, Jizhou Liu, Samuel Sokota et al.

An unaddressed challenge in multi-agent 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 learning intuitive policies. 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.

Edmond Awad, Sydney Levine, Andrea Loreggia et al.

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.

Stephanie Stacy, Chenfei Li, Minglu Zhao et al.

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.

Anirban Lahiri, Utanko Mitra, Sunreeta Sen et al.

A number of questionnaire based psychometric testing frameworks are globally for example OCEAN (Five factor) indicator, MBTI (Myers Brigg Type Indicator) etc. However, questionnaire based psychometric tests have some known shortcomings. This work explores whether these shortcomings can be mitigated through computer-based gaming platforms for evaluating psychometric parameters. A computer based psychometric game framework called Antarjami has been developed for evaluating OCEAN (Five factor) indicators. It investigates the feasibility of extracting psychometric parameters through computer-based games, utilizing underlying improvements in the area of modern artificial intelligence. The candidates for the test are subjected to a number scenarios as part of the computer based game and their reactions/responses are used to evaluate their psychometric parameters. As part of the study, the parameters obtained from the game were compared with those evaluated using paper based tests and scores given by a panel of psychologists. The achieved results were very promising.

Rose E. Wang, Sarah A. Wu, James A. Evans et al.

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. We test Bayesian Delegation in a suite of multi-agent Markov decision processes inspired by cooking problems. On these tasks, agents with Bayesian Delegation coordinate both their high-level plans (e.g. what sub-task they should work on) and their low-level actions (e.g. avoiding getting in each other's way). In a self-play evaluation, Bayesian Delegation outperforms alternative algorithms. Bayesian Delegation is also a capable ad-hoc collaborator and successfully coordinates with other agent types even in the absence of prior experience. Finally, in a behavioral experiment, we show that Bayesian Delegation makes inferences similar to human observers about the intent of others. Together, these results demonstrate the power of Bayesian Delegation for decentralized multi-agent collaboration.

Jack Serrino, Max Kleiman-Weiner, David C. Parkes et al.

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.

Michael Shum, Max Kleiman-Weiner, Michael L. Littman et al.

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.

Joseph Y. Halpern, Max Kleiman-Weiner

We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes). These, together with a definition of actual causality, provide the key ingredients for moral responsibility judgments. We show that these definitions give insight into commonsense intuitions in a variety of puzzling cases from the literature.

DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum et al.

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 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.

Edmond Awad, Sydney Levine, Max Kleiman-Weiner et al.

When a semi-autonomous car crashes and harms someone, how are blame and causal responsibility distributed across the human and machine drivers? In this article, we consider cases in which a pedestrian was hit and killed by a car being operated under shared control of a primary and a secondary driver. We find that when only one driver makes an error, that driver receives the blame and is considered causally responsible for the harm, regardless of whether that driver is a machine or a human. However, when both drivers make errors in cases of shared control between a human and a machine, the blame and responsibility attributed to the machine is reduced. This finding portends a public under-reaction to the malfunctioning AI components of semi-autonomous cars and therefore has a direct policy implication: a bottom-up regulatory scheme (which operates through tort law that is adjudicated through the jury system) could fail to properly regulate the safety of shared-control vehicles; instead, a top-down scheme (enacted through federal laws) may be called for.

Richard Kim, Max Kleiman-Weiner, Andres Abeliuk et al.

We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over abstract moral dimensions, which provide interpretable parameter values when implemented in machine-led ethical decision-making. Moreover, characterizing the social structures of individuals and groups as a hierarchical Bayesian model, we show that a useful description of an individual's moral values - as well as a group's shared values - can be inferred from a limited amount of observed data. Finally, we apply and evaluate our approach to data from the Moral Machine, a web application that collects human judgments on moral dilemmas involving autonomous vehicles.