A central challenge in statistical modeling is identifying the subset of features that belong in the true regression model. The classical best subset selection problem, recently made tractable via mixed-integer optimization (MIO), finds the globally optimal sparse solution. It does not, however, make use of any information beyond the observed data. In many applied settings, domain experts can meaningfully rank or score the relevance of candidate predictors, yet no existing framework integrates such probabilistic expert assessments directly into the best-subsets objective. This paper presents Expert-Implied Bayesian Best Subsets (EBBS), a method that incorporates domain-expert probability estimates of feature relevance into the MIO best-subsets problem through a maximum a posteriori (MAP) framework. Expert views from multiple respondents are aggregated into a single prior probability per feature using the Poisson binomial distribution for marginal probability estimates, the pairwise win rate for pairwise comparisons, or the normalized mean rank for ordinal rankings. This probability enters the objective function as a log-odds penalty term that smoothly encourages or discourages the selection of each feature consistent with the expert consensus. This paper provides analytic derivations of the MAP formulation and characterizes its theoretical properties. The proposed model reduces to Best Subsets when experts all have no views. Empirical results on synthetic and real datasets are forthcoming.

We study the ability of language models to reason about appropriate information disclosure--a central aspect of the evolving field of agentic privacy. Whereas previous works have focused on evaluating a model's ability to align with human decisions, we examine the role of ambiguity and missing context on model performance when making information-sharing decisions. We identify context ambiguity as a crucial barrier for high performance in privacy assessments. By designing Camber, a framework for context disambiguation, we show that model-generated decision rationales can reveal ambiguities and that systematically disambiguating context based on these rationales leads to significant accuracy improvements (up to 13.3% in precision and up to 22.3% in recall) as well as reductions in prompt sensitivity. Overall, our results indicate that approaches for context disambiguation are a promising way forward to enhance agentic privacy reasoning.

Large Language Models (LLMs) are being explored for applications in scientific research, including their capabilities to synthesize literature, answer research questions, generate research ideas, and even conduct computational experiments. Ultimately, our goal is for these to help scientists derive novel scientific insights. In many areas of science, such insights often arise from processing and visualizing data to understand its patterns. However, evaluating whether an LLM-mediated scientific workflow produces outputs conveying the correct scientific insights is challenging to evaluate and has not been addressed in past work. We introduce ASTROVISBENCH, the first benchmark for both scientific computing and visualization in the astronomy domain. ASTROVISBENCH judges a language model's ability to both (1) create astronomy-specific workflows to process and analyze data and (2) visualize the results of these workflows through complex plots.

TECHNOLOGY IT ARTIFICIAL INTELLIGENCE CHATGPT Illustration picture shows the ChatGPT artificial intelligence software, which generates human-like conversation, Friday 03 February 2023 in Lierde. TECHNOLOGY IT ARTIFICIAL INTELLIGENCE CHATGPT Illustration picture shows the ChatGPT artificial intelligence software, which generates human-like conversation, Friday 03 February 2023 in Lierde. A new study from the Massachusetts Institute of Technology is the latest research to find that relying too much on chatbots can diminish critical-thinking skills, and potentially decrease our ability to discern misinformation for ourselves. As AI tools are becoming more sophisticated and accessible, manipulated images and misleading headlines are becoming more common. AI can be part of the solution, and has proved useful in helping users identify fake content - but there's a cost to using it this way, the new research suggests.

To address these challenges, we introduce Refer-Judge, a novel framework that harnesses the reasoning capabilities of Multimodal Large Language Models (MLLMs) to identify and mitigate toxic data. At the core of Refer-Judge is a Jury-andJudge Chain-of-Thought paradigm, inspired by the deliberative process of the judicial system. This framework targets the root causes of annotation noise: jurors collaboratively assess 3DVG samples from diverse perspectives, providing structured, multi-faceted evaluations. Judges then consolidate these insights using a Corroborative Refinement strategy, which adaptively reorganizes information to correct ambiguities arising from biased or incomplete observations. Through this two-stage deliberation, Refer-Judge significantly enhances the reliability of data judgments. Extensive experiments demonstrate that our framework not only achieves human-level discrimination at the scene level but also improves the performance of baseline algorithms via data purification. Code is available at https://github.com/Hermione-HKX/Refer_Judge.

Moral judgment is integral to large language models' (LLMs) social reasoning. As multi-agent systems gain prominence, it becomes crucial to understand how LLMs function when collaborating compared to operating as individual agents. In human moral judgment, group deliberation leads to a Utilitarian Boost: a tendency to endorse norm violations that inflict harm but maximize benefits for the greatest number of people. We study whether a similar dynamic emerges in multi-agent LLM systems. We test six models on well-established sets of moral dilemmas across two conditions: (1) Solo, where models reason independently, and (2) Group, where they engage in multi-turn discussions in pairs or triads.

Large language models are increasingly used as judges (LLM-as-a-judge) to evaluate model outputs at scale, but their assessments often diverge systematically from human judgments.

LLM-as-a-Judge has emerged as a promising tool for automatically evaluating generated outputs, but its reliability is often undermined by potential biases in judgment. Existing efforts to mitigate these biases face key limitations: in-context learning-based methods fail to address rooted biases due to the evaluator's limited capacity for self-reflection, whereas fine-tuning is not applicable to all evaluator types, especially closed-source models. To address this challenge, we introduce the Reasoning-based Bias Detector (RBD), which is a plug-in module that identifies biased evaluations and generates structured reasoning to guide evaluator self-correction. Rather than modifying the evaluator itself, RBD operates externally and engages in an iterative process of bias detection and feedback-driven revision. To support its development, we design a complete pipeline consisting of biased dataset construction, supervision collection, distilled reasoning-based fine-tuning of RBD, and integration with LLM evaluators. We fine-tune four sizes of RBD models, ranging from 1.5B to 14B, and observe consistent performance improvements across all scales. Experimental results on 4 bias types--verbosity, position, bandwagon, and sentiment--evaluated using 8 LLM evaluators demonstrate RBD's strong effectiveness. For example, the RBD-8B model improves evaluation accuracy by an average of 18.5% and consistency by 10.9%, and surpasses prompting-based baselines and fine-tuned judges by 12.8% and 17.2%, respectively.

Christopher Marquis is a professor at the University of Cambridge and the author of The Profiteers. In 1930, in the depths of the Great Depression, John Maynard Keynes wrote a short essay called . It is often remembered for one striking prediction: by 2030, people in wealthy countries might only need to work about 15 hours a week. What Keynes imagined was a society advanced enough to solve what he called the "economic problem" of basic material provision. If technology kept improving, and societies kept growing richer, then fewer hours of human labor would be needed to produce the necessities and comforts of life.

Anthropic announced "dreaming" for AI agents to sort through "memories" at its developer conference. Anthropic just announced a new feature called "dreaming" at the company's developer conference in San Francisco. It's part of Anthropic's recently launched AI agent infrastructure designed to help users manage and deploy tools that automate software processes. This "dreaming" aspect sorts through the transcript of what an agent recently completed and attempts to glean insights to improve the agent's performance. Folks using AI agents often send them on multistep journeys, like visiting a few websites or reading multiple files, to complete online tasks.