相关论文: Information-theoretic Distinctions Between Decepti…

Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…

The prevailing technical literature in AI Safety interprets scheming and sandbagging behaviors in large language models (LLMs) as indicators of deceptive agency or hidden objectives. This transdisciplinary philosophical essay proposes an…

The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used…

In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…

Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple…

Large language models (LLMs) have the potential to boost human productivity by speeding up task completion -- provided users know when to offload cognitive work to them. But we do not know if users are well-calibrated in estimating these…

The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models may become inaccurate and need adjustment. Many technologies for…

While natural-language explanations from large language models (LLMs) are widely adopted to improve transparency and trust, their impact on objective human-AI team performance remains poorly understood. We identify a Persuasion Paradox:…

Dialogue systems often fail when user utterances are semantically complete yet lack the clarity and completeness required for appropriate system action. This mismatch arises because users frequently do not fully understand their own needs,…

As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…

An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive…

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

AI Alignment is often presented as an interaction between a single designer and an artificial agent in which the designer attempts to ensure the agent's behavior is consistent with its purpose, and risks arise solely because of conflicts…

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…

We identify a fundamental incompatibility between the goals of accuracy, trust, and human-level reasoning in artificial intelligence (AI) systems, for strict mathematical definitions of these notions. We define accuracy of a system as the…

Deep visual models are susceptible to adversarial perturbations to inputs. Although these signals are carefully crafted, they still appear noise-like patterns to humans. This observation has led to the argument that deep visual…

When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content…

As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed…

Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that…

This article introduces a conjecture that formalises a fundamental trade-off between provable correctness and broad data-mapping capacity in Artificial Intelligence (AI) systems. When an AI system is engineered for deductively watertight…