Related papers: Deceptive AI Explanations: Creation and Detection
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…
When AI systems explain their reasoning step-by-step, practitioners often assume these explanations reveal what actually influenced the AI's answer. We tested this assumption by embedding hints into questions and measuring whether models…
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'…
With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…
Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains…
Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…
Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…
Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same,…
The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…
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…
Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's…
Large Language Models (LLMs) and Large Reasoning Models (LRMs) are increasingly used for critical tasks, yet they provide no guarantees about the correctness of their solutions. Users must decide whether to trust the model's answer, aided…
Explainability in AI is gaining attention in the computer science community in response to the increasing success of deep learning and the important need of justifying how such systems make predictions in life-critical applications. The…
Algorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model…
This theoretical work examines 'hallucinations' in both human cognition and large language models, comparing how each system can produce perceptions or outputs that deviate from reality. Drawing on neuroscience and machine learning…
Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives…
Reading and evaluating product reviews is central to how most people decide what to buy and consume online. However, the recent emergence of Large Language Models and Generative Artificial Intelligence now means writing fraudulent or fake…
There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level…
Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However,…
AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice. However, fully automating such high-stakes applications can raise ethical or fairness concerns. Instead, in such cases,…