Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable, leading to inaccurate variable importance estimates and undermining their utility in critical biomedical applications. Although ensembling offers a solution, deciding whether to explain a single ensemble model or aggregate individual model explanations is difficult due to the nonlinearity of importance measures and remains largely understudied. Our theoretical analysis, developed under assumptions accommodating complex state-of-the-art ML models, reveals that this choice is primarily driven by the model's excess risk. In contrast to prior literature, we show that ensembling at the model level provides more accurate variable-importance estimates, particularly for expressive models, by reducing this leading error term. We validate these findings on classical benchmarks and a large-scale proteomic study from the UK Biobank.

Most recent research hasaddressed thisby focusing onlocal interpretability, which explains a model's individual predictions (e.g., the role of each feature in a patient's diagnosis) [25, 30, 34, 38]. Twospecial cases areS = andS = D, which respectively correspond to the mean prediction f (x ) = E[f(X)] and the full model predictionfD(x) = f(x).

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group frequently receive identical rewards, causing relative advantages to collapse and updates to vanish. We propose self-hint aligned GRPO with privileged supervision (SAGE), an on-policy reinforcement learning framework that injects privileged hints during training to reshape the rollout distribution under the same terminal verifier reward. For each prompt $x$, the model samples a compact hint $h$ (e.g., a plan or decomposition) and then generates a solution $τ$ conditioned on $(x,h)$. Crucially, the task reward $R(x,τ)$ is unchanged; hints only increase within-group outcome diversity under finite sampling, preventing GRPO advantages from collapsing under sparse rewards. At test time, we set $h=\varnothing$ and deploy the no-hint policy without any privileged information. Moreover, sampling diverse self-hints serves as an adaptive curriculum that tracks the learner's bottlenecks more effectively than fixed hints from an initial policy or a stronger external model. Experiments over 6 benchmarks with 3 LLMs show that SAGE consistently outperforms GRPO, on average +2.0 on Llama-3.2-3B-Instruct, +1.2 on Qwen2.5-7B-Instruct and +1.3 on Qwen3-4B-Instruct. The code is available at https://github.com/BaohaoLiao/SAGE.

Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.

It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these methods are ad hoc: they frequently trade off correctness for diversity, their effectiveness varies across tasks, and in some cases they even contradict one another. In this work, we place these observations on a rigorous foundation. We first provide a formal proof of why RL fine-tuning exhibits diversity collapse via a selection and reinforcement bias. Next, we make a key observation that any reward modification to address diversity collapse only needs to be applied on the correct trajectories. Building directly on this analysis, we introduce a principled method -- differential smoothing -- that provably improves both correctness and diversity, outperforming vanilla RL as well as widely used entropy-based heuristics. Our theory precisely characterizes when existing heuristics help and why they fail, while showing that differential smoothing is universally superior. Extensive experiments with models from 1B to 7B parameters, across domains including CountDown and real-world mathematical reasoning, demonstrate consistent gains. Differential smoothing improves both Pass@1 and Pass@k, with up to 6.7% improvements on AIME24 dataset.

Epidemic outcomes have a complex interplay with human behavior and beliefs. Most of the forecasting literature has focused on the task of predicting epidemic signals using simple mechanistic models or black-box models, such as deep transformers, that ingest all available signals without offering interpretability. However, to better understand the mechanisms and predict the impact of interventions, we need the ability to forecast signals associated with beliefs and behaviors in an interpretable manner. In this work, we propose a graph-based forecasting framework that first constructs a graph of interrelated signals based on trend similarity, and then applies graph neural networks (GNNs) for prediction. This approach enables interpretable analysis by revealing which signals are more predictable and which relationships contribute most to forecasting accuracy. We believe our method provides early steps towards a framework for interpretable modeling in domains with multiple potentially interdependent signals, with implications for building future simulation models that integrate behavior, beliefs, and observations.

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have emerged as a promising tool for decomposing LLM representations into more interpretable features, but explaining the features captured by SAEs remains a challenging task. In this work, we propose SAGE (SAE AGentic Explainer), an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanation-driven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanationdriven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.

Large vision-language models, such as CLIP, have shown strong zero-shot classification performance by aligning images and text in a shared embedding space. However, CLIP models often develop multimodal spurious biases, which is the undesirable tendency to rely on spurious features. For example, CLIP may infer object types in images based on frequently co-occurring backgrounds rather than the object's core features. This bias significantly impairs the robustness of pre-trained CLIP models on out-of-distribution data, where such cross-modal associations no longer hold. Existing methods for mitigating multimodal spurious bias typically require fine-tuning on downstream data or prior knowledge of the bias, which undermines the out-of-the-box usability of CLIP. In this paper, we first theoretically analyze the impact of multimodal spurious bias in zero-shot classification. Based on this insight, we propose Spuriousness-Aware Guided Exploration (SAGE), a simple and effective method that mitigates spurious bias through guided prompt selection. SAGE requires no training, fine-tuning, or external annotations. It explores a space of prompt templates and selects the prompts that induce the largest semantic separation between classes, thereby improving worst-group robustness. Extensive experiments on four real-world benchmark datasets and five popular backbone models demonstrate that SAGE consistently improves zero-shot performance and generalization, outperforming previous zero-shot approaches without any external knowledge or model updates.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO. To stabilize training, these methods typically center trajectory rewards by subtracting the empirical mean for each prompt. Statistically, this centering acts as a control variate (or baseline), reducing the variance of the policy-gradient estimator. Typically, the mean reward is estimated using per-prompt empirical averages for each prompt in a batch. Drawing inspiration from Stein's paradox, we propose using shrinkage estimators that combine per-prompt and across-prompt means to improve the overall per-prompt mean estimation accuracy -- particularly in the low-generation regime typical of RLVR. Theoretically, we construct a shrinkage-based baseline that provably yields lower-variance policy-gradient estimators across algorithms. Our proposed baseline serves as a drop-in replacement for existing per-prompt mean baselines, requiring no additional hyper-parameters or computation. Empirically, shrinkage baselines consistently outperform standard empirical-mean baselines, leading to lower-variance gradient updates and improved training stability.

As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to capture the conversational dynamics of real-world usage and the application-specific harms that emerge in context. Such potential oversights can lead to harms that go unnoticed in standard safety benchmarks and other current evaluation methodologies. To address these needs for robust AI safety evaluation, we introduce SAGE (Safety AI Generic Evaluation), an automated modular framework designed for customized and dynamic harm evaluations. SAGE employs prompted adversarial agents with diverse personalities based on the Big Five model, enabling system-aware multi-turn conversations that adapt to target applications and harm policies. We evaluate seven state-of-the-art LLMs across three applications and harm policies. Multi-turn experiments show that harm increases with conversation length, model behavior varies significantly when exposed to different user personalities and scenarios, and some models minimize harm via high refusal rates that reduce usefulness. We also demonstrate policy sensitivity within a harm category where tightening a child-focused sexual policy substantially increases measured defects across applications. These results motivate adaptive, policy-aware, and context-specific testing for safer real-world deployment.