Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems

Large language models (LLMs) enable powerful zero-shot recommendations by leveraging broad contextual knowledge, yet predictive uncertainty and embedded biases threaten reliability and fairness. This paper studies how uncertainty and fairness evaluations affect the accuracy, consistency, and trustworthiness of LLM-generated recommendations. We introduce a benchmark of curated metrics and a dataset annotated for eight demographic attributes (31 categorical values) across two domains: movies and music. Through in-depth case studies, we quantify predictive uncertainty (via entropy) and demonstrate that Google DeepMind's Gemini 1.5 Flash exhibits systematic unfairness for certain sensitive attributes; measured similarity-based gaps are SNSR at 0.1363 and SNSV at 0.0507. These disparities persist under prompt perturbations such as typographical errors and multilingual inputs. We further integrate personality-aware fairness into the RecLLM evaluation pipeline to reveal personality-linked bias patterns and expose trade-offs between personalization and group fairness. We propose a novel uncertainty-aware evaluation methodology for RecLLMs, present empirical insights from deep uncertainty case studies, and introduce a personality profile-informed fairness benchmark that advances explainability and equity in LLM recommendations. Together, these contributions establish a foundation for safer, more interpretable RecLLMs and motivate future work on multi-model benchmarks and adaptive calibration for trustworthy deployment.

Procedural Pretraining: Warming Up Language Models with Abstract Data

Pretraining directly on web-scale corpora is the de facto paradigm for building language models. We study an alternative setting where the model is initially exposed to abstract structured data, as a means to ease the subsequent acquisition of rich semantic knowledge, much like humans learn simple logic and mathematics before higher reasoning. We specifically focus on procedural data, generated by formal languages and other simple algorithms, as such abstract data. We first diagnose the algorithmic skills that different forms of procedural data can improve, often significantly. For example, on context recall (Needle-in-a-haystack), the accuracy jumps from 10 to 98% when pretraining on Dyck sequences (balanced brackets). Second, we study how these gains are reflected in pretraining larger models (up to 1.3B). We find that front-loading as little as 0.1% procedural data significantly outperforms standard pretraining on natural language, code, and informal mathematics (C4, CodeParrot, and DeepMind-Math datasets). Notably, this procedural pretraining enables the models to reach the same loss value with only 55, 67, 86% of the original data. Third, we explore the mechanisms behind and find that procedural pretraining instils non-trivial structure in both attention and MLP layers. The former is particularly important for structured domains (e.g. code), and the latter for language. Finally, we lay a path for combining multiple forms of procedural data. Our results show that procedural pretraining is a simple, lightweight means to improving performance and accelerating language model pretraining, ultimately suggesting the promise of disentangling knowledge acquisition from reasoning in LLMs.

Learning to Advect: A Neural Semi-Lagrangian Architecture for Weather Forecasting

Recent machine-learning approaches to weather forecasting often employ a monolithic architecture, where distinct physical mechanisms (advection, transport), diffusion-like mixing, thermodynamic processes, and forcing are represented implicitly within a single large network. This representation is particularly problematic for advection, where long-range transport must be treated with expensive global interaction mechanisms or through deep, stacked convolutional layers. To mitigate this, we present PARADIS, a physics-inspired global weather prediction model that imposes inductive biases on network behavior through a functional decomposition into advection, diffusion, and reaction blocks acting on latent variables. We implement advection through a Neural Semi-Lagrangian operator that performs trajectory-based transport via differentiable interpolation on the sphere, enabling end-to-end learning of both the latent modes to be transported and their characteristic trajectories. Diffusion-like processes are modeled through depthwise-separable spatial mixing, while local source terms and vertical interactions are modeled via pointwise channel interactions, enabling operator-level physical structure. PARADIS provides state-of-the-art forecast skill at a fraction of the training cost. On ERA5-based benchmarks, the 1 degree PARADIS model, with a total training cost of less than a GPU month, meets or exceeds the performance of 0.25 degree traditional and machine-learning baselines, including the ECMWF HRES forecast and DeepMind's GraphCast.

From Observations to Events: Event-Aware World Model for Reinforcement Learning

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious variations such as textures or color shifts. From a cognitive science perspective, humans segment continuous sensory streams into discrete events and rely on these key events for decision-making. Motivated by this principle, we propose the Event-Aware World Model (EAWM), a general framework that learns event-aware representations to streamline policy learning without requiring handcrafted labels. EAWM employs an automated event generator to derive events from raw observations and introduces a Generic Event Segmentor (GES) to identify event boundaries, which mark the start and end time of event segments. Through event prediction, the representation space is shaped to capture meaningful spatio-temporal transitions. Beyond this, we present a unified formulation of seemingly distinct world model architectures and show the broad applicability of our methods. Experiments on Atari 100K, Craftax 1M, and DeepMind Control 500K, DMC-GB2 500K demonstrate that EAWM consistently boosts the performance of strong MBRL baselines by 10%-45%, setting new state-of-the-art results across benchmarks. Our code is released at https://github.com/MarquisDarwin/EAWM.

ARC Prize 2025: Technical Report

The ARC-AGI benchmark series serves as a critical measure of few-shot generalization on novel tasks, a core aspect of intelligence. The ARC Prize 2025 global competition targeted the newly released ARC-AGI-2 dataset, which features greater task complexity compared to its predecessor. The Kaggle competition attracted 1,455 teams and 15,154 entries, with the top score reaching 24% on the ARC-AGI-2 private evaluation set. Paper submissions nearly doubled year-over-year to 90 entries, reflecting the growing research interest in fluid intelligence and abstract reasoning. The defining theme of 2025 is the emergence of the refinement loop -- a per-task iterative program optimization loop guided by a feedback signal. Refinement loops come in a variety of forms, in particular evolutionary program synthesis approaches and application-layer refinements to commercial AI systems. Such refinement loops are also possible in weight space, as evidenced by zero-pretraining deep learning methods which are now achieving competitive performance with remarkably small networks (7M parameters). In parallel, four frontier AI labs (Anthropic, Google DeepMind, OpenAI, and xAI) reported ARC-AGI performance in public model cards in 2025, establishing ARC-AGI as an industry standard benchmark for AI reasoning. However, our analysis indicates that current frontier AI reasoning performance remains fundamentally constrained to knowledge coverage, giving rise to new forms of benchmark contamination. In this paper, we survey the top-performing methods, examine the role of refinement loops in AGI progress, discuss knowledge-dependent overfitting, and preview ARC-AGI-3, which introduces interactive reasoning challenges that require exploration, planning, memory, goal acquisition, and alignment capabilities.

Reward Learning through Ranking Mean Squared Error

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified. Recent work has proposed learning reward functions from human feedback in the form of ratings, rather than traditional binary preferences, enabling richer and potentially less cognitively demanding supervision. Building on this paradigm, we introduce a new rating-based RL method, Ranked Return Regression for RL (R4). At its core, R4 employs a novel ranking mean squared error (rMSE) loss, which treats teacher-provided ratings as ordinal targets. Our approach learns from a dataset of trajectory-rating pairs, where each trajectory is labeled with a discrete rating (e.g., "bad," "neutral," "good"). At each training step, we sample a set of trajectories, predict their returns, and rank them using a differentiable sorting operator (soft ranks). We then optimize a mean squared error loss between the resulting soft ranks and the teacher's ratings. Unlike prior rating-based approaches, R4 offers formal guarantees: its solution set is provably minimal and complete under mild assumptions. Empirically, using simulated human feedback, we demonstrate that R4 consistently matches or outperforms existing rating and preference-based RL methods on robotic locomotion benchmarks from OpenAI Gym and the DeepMind Control Suite, while requiring significantly less feedback.

Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features

Large data-driven physics models like DeepMind's weather model GraphCast have empirically succeeded in parameterizing time operators for complex dynamical systems with an accuracy reaching or in some cases exceeding that of traditional physics-based solvers. Unfortunately, how these data-driven models perform computations is largely unknown and whether their internal representations are interpretable or physically consistent is an open question. Here, we adapt tools from interpretability research in Large Language Models to analyze intermediate computational layers in GraphCast, leveraging sparse autoencoders to discover interpretable features in the neuron space of the model. We uncover distinct features on a wide range of length and time scales that correspond to tropical cyclones, atmospheric rivers, diurnal and seasonal behavior, large-scale precipitation patterns, specific geographical coding, and sea-ice extent, among others. We further demonstrate how the precise abstraction of these features can be probed via interventions on the prediction steps of the model. As a case study, we sparsely modify a feature corresponding to tropical cyclones in GraphCast and observe interpretable and physically consistent modifications to evolving hurricanes. Such methods offer a window into the black-box behavior of data-driven physics models and are a step towards realizing their potential as trustworthy predictors and scientifically valuable tools for discovery.

Harvesting AlphaEarth: Benchmarking the Geospatial Foundation Model for Agricultural Downstream Tasks

Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introduced AlphaEarth Foundation (AEF), a GFM pre-trained using multi-source EOs across continuous time. An annual and global embedding dataset is produced using AEF that is ready for analysis and modeling. The internal experiments show that AEF embeddings have outperformed operational models in 15 EO tasks without re-training. However, those experiments are mostly about land cover and land use classification. Applying AEF and other GFMs to agricultural monitoring require an in-depth evaluation in critical agricultural downstream tasks. There is also a lack of comprehensive comparison between the AEF-based models and traditional remote sensing (RS)-based models under different scenarios, which could offer valuable guidance for researchers and practitioners. This study addresses some of these gaps by evaluating AEF embeddings in three agricultural downstream tasks in the U.S., including crop yield prediction, tillage mapping, and cover crop mapping. Datasets are compiled from both public and private sources to comprehensively evaluate AEF embeddings across tasks at different scales and locations, and RS-based models are trained as comparison models. AEF-based models generally exhibit strong performance on all tasks and are competitive with purpose-built RS-based models in yield prediction and county-level tillage mapping when trained on local data. However, we also find several limitations in current AEF embeddings, such as limited spatial transferability compared to RS-based models, low interpretability, and limited time sensitivity. These limitations recommend caution when applying AEF embeddings in agriculture, where time sensitivity, generalizability, and interpretability is important.

Spectral Representation-based Reinforcement Learning

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful approximations such as neural networks offer great expressiveness, they often present theoretical ambiguities, suffer from optimization instability and exploration difficulty, and incur substantial computational costs in practice. In this paper, we introduce the perspective of spectral representations as a solution to address these difficulties in RL. Stemming from the spectral decomposition of the transition operator, this framework yields an effective abstraction of the system dynamics for subsequent policy optimization while also providing a clear theoretical characterization. We reveal how to construct spectral representations for transition operators that possess latent variable structures or energy-based structures, which implies different learning methods to extract spectral representations from data. Notably, each of these learning methods realizes an effective RL algorithm under this framework. We also provably extend this spectral view to partially observable MDPs. Finally, we validate these algorithms on over 20 challenging tasks from the DeepMind Control Suite, where they achieve performances comparable or superior to current state-of-the-art model-free and model-based baselines.

Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, LLaMA

Prompt engineering has emerged as a critical factor influencing large language model (LLM) performance, yet the impact of pragmatic elements such as linguistic tone and politeness remains underexplored, particularly across different model families. In this work, we propose a systematic evaluation framework to examine how interaction tone affects model accuracy and apply it to three recently released and widely available LLMs: GPT-4o mini (OpenAI), Gemini 2.0 Flash (Google DeepMind), and Llama 4 Scout (Meta). Using the MMMLU benchmark, we evaluate model performance under Very Friendly, Neutral, and Very Rude prompt variants across six tasks spanning STEM and Humanities domains, and analyze pairwise accuracy differences with statistical significance testing. Our results show that tone sensitivity is both model-dependent and domain-specific. Neutral or Very Friendly prompts generally yield higher accuracy than Very Rude prompts, but statistically significant effects appear only in a subset of Humanities tasks, where rude tone reduces accuracy for GPT and Llama, while Gemini remains comparatively tone-insensitive. When performance is aggregated across tasks within each domain, tone effects diminish and largely lose statistical significance. Compared with earlier researches, these findings suggest that dataset scale and coverage materially influence the detection of tone effects. Overall, our study indicates that while interaction tone can matter in specific interpretive settings, modern LLMs are broadly robust to tonal variation in typical mixed-domain use, providing practical guidance for prompt design and model selection in real-world deployments.