Related papers: Confirmation bias: A challenge for scalable oversi…

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using…

Algorithmic decision-making systems are increasingly used throughout the public and private sectors to make important decisions or assist humans in making these decisions with real social consequences. While there has been substantial…

Although the integration of artificial intelligence (AI) into everyday tasks improves efficiency and objectivity, it also risks transmitting bias to human decision-making. In this study, we conducted a controlled experiment that simulated…

Human-AI collaboration increasingly drives decision-making across industries, from medical diagnosis to content moderation. While AI systems promise efficiency gains by providing automated suggestions for human review, these workflows can…

Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs significant environmental, economic, and ethical costs,…

Artificial Intelligence (AI) systems are not intrinsically neutral and biases trickle in any type of technological tool. In particular when dealing with people, the impact of AI algorithms' technical errors originating with mislabeled data…

In many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure…

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

Assessing an AI system's behavior-particularly in Explainable AI Systems-is sometimes done empirically, by measuring people's abilities to predict the agent's next move-but how to perform such measurements? In empirical studies with humans,…

Automated decision systems (ADS) have become ubiquitous in many high-stakes domains. Those systems typically involve sophisticated yet opaque artificial intelligence (AI) techniques that seldom allow for full comprehension of their inner…

In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under…

Understanding how humans revise their beliefs in light of new information is crucial for developing AI systems which can effectively model, and thus align with, human reasoning. While theoretical belief revision frameworks rely on a set of…

Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of post-hoc explanations. We investigate this relationship by evaluating 11 computer vision…

Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as document analysis, question answering (Q&A), and literature search. However, system…

Machine learning models only provide probabilistic guarantees on the expected loss of random samples from the distribution represented by their training data. As a result, a model with high accuracy, may or may not be reliable for…

In the era of Model-as-a-Service, organizations increasingly rely on third-party AI models for rapid deployment. However, the dynamic nature of emerging AI applications, the continual introduction of new datasets, and the growing number of…

Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges induce bias in naive evaluation scores. We propose a simple…

Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from training data. Typical approaches to achieve fairness…

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…

Many safety failures in machine learning arise when models are used to assign predictions to people (often in settings like lending, hiring, or content moderation) without accounting for how individuals can change their inputs. In this…