This happened as generative and agentic systems became essential in key sectors worldwide. This feature highlights the major AI ethics and policy developments of 2025, and concludes with a forward-looking perspective on the ethical and policy challenges likely to shape 2026.

What does it mean to have speech without a speaker? For the first time, speech has been decoupled from consequence. We now live alongside AI systems that converse knowledgeably and persuasively--deploying claims about the world, explanations, advice, encouragement, apologies, and promises--while bearing no vulnerability for what they say. Millions of people already rely on chatbots powered by large language models, and have integrated these synthetic interlocutors into their personal and professional lives. An LLM's words shape our beliefs, decisions, and actions, yet no speaker stands behind them. This dynamic is already familiar in everyday use. A chatbot gets something wrong. When corrected, it apologizes and changes its answer.

Neural Information Processing Systems http://nips.cc/

Machine learning has provided a universal toolbox enhancing the decision making in many disciplines from advertising and recommender systems toeducation andcriminal justice.

Forinstance, theproportions ofpotential loan applicants ineach group that will seek higher wages, falsify income, or forego application mightchangeif banks use new policies toapproveordenyloans, possibly counteracting fairintent.

We examine whether these static fairness constraints mitigate or worsen the qualification disparity in the long-run. Our work can be applied to a variety of applications such as recruitment and bank lending. In these applications, aninstitute observesindividuals' features (e.g., credit scores), and makes myopic decisions(e.g., issue loans) by assessing such features against some variables of interest (e.g., ability torepay) which are unknown and unobservable tothe institute when making decisions.

Importantly,thesuccess ofanymitigation strategystrongly depends on the structure of the shift. Despite this, there has been little discussion of how toempirically assess the structure ofadistribution shift that one isencountering in practice. In this work, we adopt a causal framing to motivate conditional independence tests as akeytool for characterizing distribution shifts. Using our approach in two medical applications, we show that this knowledge can help diagnose failures offairness transfer,including cases where real-world shifts are more complexthanisoften assumed intheliterature.

Theuseofmetric elicitation enables a practitioner to tune the performance and fairness metrics to the task, context,andpopulationathand.