Related papers: Lie detection algorithms attract few users but vas…
The use of Artificial Intelligence (AI), or more generally data-driven algorithms, has become ubiquitous in today's society. Yet, in many cases and especially when stakes are high, humans still make final decisions. The critical question,…
Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI…
The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…
Partner selection is crucial for cooperation and hinges on communication. As artificial agents, especially those powered by large language models (LLMs), become more autonomous, intelligent, and persuasive, they compete with humans for…
An implicit expectation of asking users to rate agents, such as an AI decision-aid, is that they will use only relevant information -- ask them about an agent's benevolence, and they should consider whether or not it was kind. Behavioral…
This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical…
Fact checking can be an effective strategy against misinformation, but its implementation at scale is impeded by the overwhelming volume of information online. Recent artificial intelligence (AI) language models have shown impressive…
The problem of detecting scientific fraud using machine learning was recently introduced, with initial, positive results from a model taking into account various general indicators. The results seem to suggest that writing style is…
Given the fast rise of increasingly autonomous artificial agents and robots, a key acceptability criterion will be the possible moral implications of their actions. In particular, intelligent persuasive systems (systems designed to…
We document a fundamental paradox in AI transparency: explanations improve decisions when algorithms are correct but systematically worsen them when algorithms err. In an experiment with 257 medical students making 3,855 diagnostic…
As the world is becoming more dependent on the internet for information exchange, some overzealous journalists, hackers, bloggers, individuals and organizations tend to abuse the gift of free information environment by polluting it with…
Recent advances in generative AI technologies like large language models have boosted the incorporation of AI assistance in writing workflows, leading to the rise of a new paradigm of human-AI co-creation in writing. To understand how…
How much are we to trust a decision made by an AI algorithm? Trusting an algorithm without cause may lead to abuse, and mistrusting it may similarly lead to disuse. Trust in an AI is only desirable if it is warranted; thus, calibrating…
Advances in machine learning have created new opportunities to develop artificial intelligence (AI)-based clinical decision support systems using past clinical data and improve diagnosis decisions in life-threatening illnesses such breast…
Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance,…
Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…
Should firms that apply machine learning algorithms in their decision-making make their algorithms transparent to the users they affect? Despite growing calls for algorithmic transparency, most firms have kept their algorithms opaque,…
We consider the use of machine learning for hypothesis testing with an emphasis on target detection. Classical model-based solutions rely on comparing likelihoods. These are sensitive to imperfect models and are often computationally…
Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who…
Deception detection has attracted increasing attention due to its importance in real-world scenarios. Its main goal is to detect deceptive behaviors from multimodal clues such as gestures, facial expressions, prosody, etc. However, these…