相关论文: Information-theoretic Distinctions Between Decepti…

The advances in artificial intelligence enabled by deep learning architectures are undeniable. In several cases, deep neural network driven models have surpassed human level performance in benchmark autonomy tasks. The underlying policies…

Large Language Models (LLMs) act as powerful reasoning engines but struggle with "symbol grounding" in embodied environments, particularly when information is asymmetrically distributed. We investigate the Privileged Information Bias (or…

Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymaking. While LLMs can excel at many such tasks, they also fail in ways that are poorly…

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for…

As AI systems increasingly assume roles where trust and alignment with human values are essential, understanding when and why they engage in deception has become a critical research priority. We introduce The Traitors, a multi-agent…

Current AI systems, grounded in oversimplified neuroscience, risk eroding the distinction between truth and falsehood. They maximize reward by amplifying attention to information without intrinsic precision mechanisms to assess whether it…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

We study the design of autonomous agents that are capable of deceiving outside observers about their intentions while carrying out tasks in stochastic, complex environments. By modeling the agent's behavior as a Markov decision process, we…

As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss…

Large language models (LLMs) can provide users with false, inaccurate, or misleading information, and we consider the output of this type of information as what Natale (2021) calls `banal' deceptive behaviour. Here, we investigate peoples'…

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Can deception exist in differential games? We provide a case study for a Turret-Attacker differential game, where two Attackers seek to score points by reaching a target region while a Turret tries to minimize the score by aligning itself…

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…

Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding misinformation and persuasion do not adequately address. This paper proposes that a significant…

Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. This phenomenon presents a critical challenge in text generation by…

Establishing shared goals is a fundamental step in human-AI communication. However, ambiguities can lead to outputs that seem correct but fail to reflect the speaker's intent. In this paper, we explore this issue with a focus on the data…

Artificial intelligence (AI) is increasingly integrated into modern healthcare, offering powerful support for clinical decision-making. However, in real-world settings, AI systems may experience performance degradation over time, due to…

There is much discussion of the false outputs that generative AI systems such as ChatGPT, Claude, Gemini, DeepSeek, and Grok create. In popular terminology, these have been dubbed AI hallucinations. However, deeming these AI outputs…

Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation…

Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and target commitment over multiple turns. Existing approaches…