相关论文: Modeling Belief in Dynamic Systems, Part I: Founda…

Under what circumstances can a system be said to have beliefs and goals, and how do such agency-related features relate to its physical state? Recent work has proposed a notion of interpretation map, a function that maps the state of a…

There is growing concern about misinformation and the role online media plays in social polarization. Analyzing belief dynamics is one way to enhance our understanding of these problems. Existing analytical tools, such as survey research or…

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable…

Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the loss function used for training. However, the meta-alignment…

Conversational AI has a fundamental flaw as a knowledge interface: sycophantic chatbots induce epistemic entrenchment and delusional belief spirals even in rational agents. We propose the problem does not stem from the AI model, rooted…

This work studies the distributed learning process on a network of agents. Agents make partial observation about an unknown hypothesis and iteratively share their beliefs over a set of possible hypotheses with their neighbors to learn the…

As large language models (LLMs) continue to demonstrate remarkable abilities across various domains, computer scientists are developing methods to understand their cognitive processes, particularly concerning how (and if) LLMs internally…

Strong artificial intelligence (AI) is envisioned to possess general cognitive abilities and scientific creativity comparable to human intelligence, encompassing both knowledge acquisition and problem-solving. While remarkable progress has…

In multi-agent reinforcement learning, the problem of learning to act is particularly difficult because the policies of co-players may be heavily conditioned on information only observed by them. On the other hand, humans readily form…

AGM's belief revision is one of the main paradigms in the study of belief change operations. Recently, several logics for belief and information change have been proposed in the literature and used to encode belief change operations in rich…

The monitoring and control of any dynamic system depends crucially on the ability to reason about its current status and its future trajectory. In the case of a stochastic system, these tasks typically involve the use of a belief state- a…

Artificial Intelligence (AI) is an integral part of our daily technology use and will likely be a critical component of emerging technologies. However, negative user preconceptions may hinder adoption of AI-based decision making. Prior work…

Humans with an average level of social cognition can infer the beliefs of others based solely on the nonverbal communication signals (e.g. gaze, gesture, pose and contextual information) exhibited during social interactions. This social…

Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent hypothesis space over which this inference operates remains unclear. In this work, we…

As multi-agent systems are increasingly utilized for reasoning and decision-making applications, there is a greater need for LLM-based agents to have something resembling propositional beliefs. One simple method for doing so is to include…

Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a principled mechanism to use those beliefs during generation. We…

People naturally bring their prior beliefs to bear on how they interpret the new information, yet few formal models exist for accounting for the influence of users' prior beliefs in interactions with data presentations like visualizations.…

Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2)…

Social biases and belief-driven behaviors can significantly impact Large Language Models (LLMs) decisions on several tasks. As LLMs are increasingly used in multi-agent systems for societal simulations, their ability to model fundamental…

In an ideal setting for Bayesian agents, a perfect description of the rules of the environment (i.e., the objective observation model) is available, allowing them to reason through the Bayesian posterior to update their beliefs in an…