Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. We present a large-scale audit of LLMs' treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveal that LLMs consistently favor low-SES applicants -- even when controlling for academic performance -- and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs' reasoning behaviors in sensitive applications.

There is an increasing imperative to integrate programming platforms within AI frameworks to enhance educational tasks for both teachers and students. However, commonly used platforms such as Code.org, Scratch, and Snap fall short of providing the desired AI features and lack adaptability for interdisciplinary applications. This study explores how educational platforms can be improved by incorporating AI and analytics features to create more effective learning environments across various subjects and domains. We interviewed 8 K-12 teachers and asked their practices and needs while using any block-based programming (BBP) platform in their classes. We asked for their approaches in assessment, course development and expansion of resources, and student monitoring in their classes. Thematic analysis of the interview transcripts revealed both commonalities and differences in the AI tools needed between the STEM and non-STEM groups. Our results indicated advanced AI features that could promote BBP platforms. Both groups stressed the need for integrity and plagiarism checks, AI adaptability, customized rubrics, and detailed feedback in assessments. Non-STEM teachers also emphasized the importance of creative assignments and qualitative assessments. Regarding resource development, both AI tools desired for updating curricula, tutoring libraries, and generative AI features. Non-STEM teachers were particularly interested in supporting creative endeavors, such as art simulations. For student monitoring, both groups prioritized desktop control, daily tracking, behavior monitoring, and distraction prevention tools. Our findings identify specific AI-enhanced features needed by K-12 teachers across various disciplines and lay the foundation for creating more efficient, personalized, and engaging educational experiences.

Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment and efficient use of data. Yet these advantages create challenges for statistical inference due to adaptivity. A fundamental property that supports valid inference is policy convergence, meaning that action-selection probabilities converge in probability given the context. Convergence ensures replicability of adaptive experiments and stability of online algorithms. In this paper, we highlight a previously overlooked issue: widely used algorithms such as LinUCB may fail to converge when the reward model is misspecified, and such non-convergence creates fundamental obstacles for statistical inference. This issue is practically important, as misspecified models -- such as linear approximations of complex dynamic system -- are often employed in real-world adaptive experiments to balance bias and variance. Motivated by this insight, we propose and analyze a broad class of algorithms that are guaranteed to converge even under model misspecification. Building on this guarantee, we develop a general inference framework based on an inverse-probability-weighted Z-estimator (IPW-Z) and establish its asymptotic normality with a consistent variance estimator. Simulation studies confirm that the proposed method provides robust and data-efficient confidence intervals, and can outperform existing approaches that exist only in the special case of offline policy evaluation. Taken together, our results underscore the importance of designing adaptive algorithms with built-in convergence guarantees to enable stable experimentation and valid statistical inference in practice.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Students arrive for the first day of school at 24th Street Elementary School. This is read by an automated voice. Please report any issues or inconsistencies here . Kindergartners have California's highest chronic absenteeism rates, with 26% missing at least 10% of school days in 2023-24.

In my experience, every kind of writing requires some kind of self-soothing Jedi mind trick, and, when it comes to essay composition, the rectangle is mine. What had seemed an impossible task transformed into a practical matter of six little arrows. The first essay anybody writes is for school. But the only examples I remember are the ones I wrote at the end, in my A-level exams. One compared Hitler to Stalin. I was proudest of the essay that considered whether the poet John Milton--pace William Blake--was "of the devil's party without knowing it." I did well on those standardized tests, but even passing was far from a foregone conclusion. I'd screwed up my mocks, the year before, smoking too much weed and studying rarely. Since then, I'd cleaned up my act--a bit--but was still overwhelmed by the task before me. My rested on a few essays written in the school hall under a three-hour time constraint?

In reinforcement learning with sparse rewards, demonstrations can accelerate learning, but determining when to imitate them remains challenging. We propose Smooth Policy Regularisation from Demonstrations (SPReD), a framework that addresses the fundamental question: when should an agent imitate a demonstration versus follow its own policy? SPReD uses ensemble methods to explicitly model Q-value distributions for both demonstration and policy actions, quantifying uncertainty for comparisons. We develop two complementary uncertainty-aware methods: a probabilistic approach estimating the likelihood of demonstration superiority, and an advantage-based approach scaling imitation by statistical significance. Unlike prevailing methods (e.g. Q-filter) that make binary imitation decisions, SPReD applies continuous, uncertainty-proportional regularisation weights, reducing gradient variance during training. Despite its computational simplicity, SPReD achieves remarkable gains in experiments across eight robotics tasks, outperforming existing approaches by up to a factor of 14 in complex tasks while maintaining robustness to demonstration quality and quantity. Our code is available at https://github.com/YujieZhu7/SPReD.

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to improve prediction by leveraging information from network neighbors. Multiple methods taking advantage of this opportunity are now available, but many, including graph neural networks, are not easily interpretable, limiting their usefulness for understanding how a model makes its predictions. Others, such as network-assisted linear regression, are interpretable but often yield substantially worse prediction performance. We bridge this gap by proposing a family of flexible network-assisted models built upon a generalization of random forests (RF+), which achieves highly-competitive prediction accuracy and can be interpreted through feature importance measures. In particular, we develop a suite of interpretation tools that enable practitioners to not only identify important features that drive model predictions, but also quantify the importance of the network contribution to prediction. Importantly, we provide both global and local importance measures as well as sample influence measures to assess the impact of a given observation. This suite of tools broadens the scope and applicability of network-assisted machine learning for high-impact problems where interpretability and transparency are essential.

Discharge communication is a critical yet underexplored component of patient care, where the goal shifts from diagnosis to education. While recent large language model (LLM) benchmarks emphasize in-visit diagnostic reasoning, they fail to evaluate models' ability to support patients after the visit. We introduce DischargeSim, a novel benchmark that evaluates LLMs on their ability to act as personalized discharge educators. DischargeSim simulates post-visit, multi-turn conversations between LLM-driven DoctorAgents and PatientAgents with diverse psychosocial profiles (e.g., health literacy, education, emotion). Interactions are structured across six clinically grounded discharge topics and assessed along three axes: (1) dialogue quality via automatic and LLM-as-judge evaluation, (2) personalized document generation including free-text summaries and structured AHRQ checklists, and (3) patient comprehension through a downstream multiple-choice exam. Experiments across 18 LLMs reveal significant gaps in discharge education capability, with performance varying widely across patient profiles. Notably, model size does not always yield better education outcomes, highlighting trade-offs in strategy use and content prioritization. DischargeSim offers a first step toward benchmarking LLMs in post-visit clinical education and promoting equitable, personalized patient support.

Effective interdisciplinary communication is frequently hindered by domain-specific jargon. To explore the jargon barriers in-depth, we conducted a formative diary study with 16 professionals, revealing critical limitations in current jargon-management strategies during workplace meetings. Based on these insights, we designed ParseJargon, an interactive LLM-powered system providing real-time personalized jargon identification and explanations tailored to users' individual backgrounds. A controlled experiment comparing ParseJargon against baseline (no support) and general-purpose (non-personalized) conditions demonstrated that personalized jargon support significantly enhanced participants' comprehension, engagement, and appreciation of colleagues' work, whereas general-purpose support negatively affected engagement. A follow-up field study validated ParseJargon's usability and practical value in real-time meetings, highlighting both opportunities and limitations for real-world deployment. Our findings contribute insights into designing personalized jargon support tools, with implications for broader interdisciplinary and educational applications.

The training of high-quality, robust machine learning models for speech-driven 3D facial animation requires a large, diverse dataset of high-quality audio-animation pairs. To overcome the lack of such a dataset, recent work has introduced large pre-trained speech encoders that are robust to variations in the input audio and, therefore, enable the facial animation model to generalize across speakers, audio quality, and languages. However, the resulting facial animation models are prohibitively large and lend themselves only to offline inference on a dedicated machine. In this work, we explore on-device, real-time facial animation models in the context of game development. We overcome the lack of large datasets by using hybrid knowledge distillation with pseudo-labeling. Given a large audio dataset, we employ a high-performing teacher model to train very small student models. In contrast to the pre-trained speech encoders, our student models only consist of convolutional and fully-connected layers, removing the need for attention context or recurrent updates. In our experiments, we demonstrate that we can reduce the memory footprint to up to 3.4 MB and required future audio context to up to 81 ms while maintaining high-quality animations. This paves the way for on-device inference, an important step towards realistic, model-driven digital characters.