Real-world machine learning applications often involve data from multiple modalities that must be integrated effectively to make robust predictions. However, in many practical settings, not all modalities are available for every sample, and acquiring additional modalities can be costly. This raises the question: which samples should be prioritized for additional modality acquisition when resources are limited? While prior work has explored individual-level acquisition strategies and training-time active learning paradigms, test-time and cohort-based acquisition remain underexplored. We introduce Cohort-based Active Modality Acquisition (CAMA), a novel test-time setting to formalize the challenge of selecting which samples should receive additional modalities. We derive acquisition strategies that leverage a combination of generative imputation and discriminative modeling to estimate the expected benefit of acquiring missing modalities based on common evaluation metrics. We also introduce upper-bound heuristics that provide performance ceilings to benchmark acquisition strategies. Experiments on multimodal datasets with up to 15 modalities demonstrate that our proposed imputation-based strategies can more effectively guide the acquisition of additional modalities for selected samples compared with methods relying solely on unimodal information, entropy-based guidance, or random selection. We showcase the real-world relevance and scalability of our method by demonstrating its ability to effectively guide the costly acquisition of proteomics data for disease prediction in a large prospective cohort, the UK Biobank (UKBB). Our work provides an effective approach for optimizing modality acquisition at the cohort level, enabling more effective use of resources in constrained settings.

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for identifying unsafe content and its categories, their generative architecture inherently lacks direct class-level probabilities, which hinders model confidence assessment and performance interpretation. This limitation complicates the setting of dynamic thresholds for content moderation and impedes fine-grained error analysis. This research proposes and evaluates three novel token-level probability estimation approaches to bridge this gap. The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models. Through extensive experimentation on a synthetically generated, rigorously annotated dataset, it is demonstrated that leveraging token logits significantly improves the interpretability and reliability of generative classifiers, enabling more nuanced content safety moderation.

Estimating the difficulty of exam questions is essential for developing good exams, but professors are not always good at this task. We compare various Large Language Model-based methods with three professors in their ability to estimate what percentage of students will give correct answers on True/False exam questions in the areas of Neural Networks and Machine Learning. Our results show that the professors have limited ability to distinguish between easy and difficult questions and that they are outperformed by directly asking Gemini 2.5 to solve this task. Yet, we obtained even better results using uncertainties of the LLMs solving the questions in a supervised learning setting, using only 42 training samples. We conclude that supervised learning using LLM uncertainty can help professors better estimate the difficulty of exam questions, improving the quality of assessment.

Large language models (LLMs) show promise in solving scientific problems. They can help generate long-form answers for scientific questions, which are crucial for comprehensive understanding of complex phenomena that require detailed explanations spanning multiple interconnected concepts and evidence. However, LLMs often suffer from hallucination, especially in the challenging task of long-form scientific question answering. Retrieval-Augmented Generation (RAG) approaches can ground LLMs by incorporating external knowledge sources to improve trustworthiness. In this context, scientific simulators, which play a vital role in validating hypotheses, offer a particularly promising retrieval source to mitigate hallucination and enhance answer factuality. However, existing RAG approaches cannot be directly applied for scientific simulation-based retrieval due to two fundamental challenges: how to retrieve from scientific simulators, and how to efficiently verify and update long-form answers. To overcome these challenges, we propose the simulator-based RAG framework (SimulRAG) and provide a long-form scientific QA benchmark covering climate science and epidemiology with ground truth verified by both simulations and human annotators. In this framework, we propose a generalized simulator retrieval interface to transform between textual and numerical modalities. We further design a claim-level generation method that utilizes uncertainty estimation scores and simulator boundary assessment (UE+SBA) to efficiently verify and update claims. Extensive experiments demonstrate SimulRAG outperforms traditional RAG baselines by 30.4% in informativeness and 16.3% in factuality. UE+SBA further improves efficiency and quality for claim-level generation.

Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control. While deep learning models excel at capturing complex dynamics, currently, their deployment is limited due to physical inconsistency and robustness, hence constraining their reliability in regulated environments. We introduce process-informed forecasting (PIF) models for temperature in pharmaceutical lyophilization. We investigate a wide range of models, from classical ones such as Autoregressive Integrated Moving Average Model (ARIMA) and Exponential Smoothing Model (ETS), to modern deep learning architectures, including Kolmogorov-Arnold Networks (KANs). We compare three different loss function formulations that integrate a process-informed trajectory prior: a fixed-weight loss, a dynamic uncertainty-based loss, and a Residual-Based Attention (RBA) mechanism. We evaluate all models not only for accuracy and physical consistency but also for robustness to sensor noise. Furthermore, we test the practical generalizability of the best model in a transfer learning scenario on a new process. Our results show that PIF models outperform their data-driven counterparts in terms of accuracy, physical plausibility and noise resilience. This work provides a roadmap for developing reliable and generalizable forecasting solutions for critical applications in the pharmaceutical manufacturing landscape.

UnScientify, a system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique to identify verbally expressed uncertainty in scientific texts and their authorial references. The core methodology of UnScientify is based on a multi-faceted pipeline that integrates span pattern matching, complex sentence analysis and author reference checking. This approach streamlines the labeling and annotation processes essential for identifying scientific uncertainty, covering a variety of uncertainty expression types to support diverse applications including information retrieval, text mining and scientific document processing. The evaluation results highlight the trade-offs between modern large language models (LLMs) and the UnScientify system. UnScientify, which employs more traditional techniques, achieved superior performance in the scientific uncertainty detection task, attaining an accuracy score of 0.808. This finding underscores the continued relevance and efficiency of UnScientify's simple rule-based and pattern matching strategy for this specific application. The results demonstrate that in scenarios where resource efficiency, interpretability, and domain-specific adaptability are critical, traditional methods can still offer significant advantages.

Despite the vast body of literature on Active Learning (AL), there is no comprehensive and open benchmark allowing for efficient and simple comparison of proposed samplers. Additionally, the variability in experimental settings across the literature makes it difficult to choose a sampling strategy, which is critical due to the one-off nature of AL experiments. To address those limitations, we introduce OpenAL, a flexible and open-source framework to easily run and compare sampling AL strategies on a collection of realistic tasks. The proposed benchmark is augmented with interpretability metrics and statistical analysis methods to understand when and why some samplers outperform others. Last but not least, practitioners can easily extend the benchmark by submitting their own AL samplers.

Hazard detection and avoidance is a key technology for future robotic small body sample return and lander missions. Current state-of-the-practice methods rely on high-fidelity, a priori terrain maps, which require extensive human-in-the-loop verification and expensive reconnaissance campaigns to resolve mapping uncertainties. We propose a novel safety mapping paradigm that leverages deep semantic segmentation techniques to predict landing safety directly from a single monocular image, thus reducing reliance on high-fidelity, a priori data products. We demonstrate precise and accurate safety mapping performance on real in-situ imagery of prospective sample sites from the OSIRIS-REx mission. INTRODUCTION Hazard detection and avoidance (HD&A) is a key technology for future robotic small body sample return and lander missions.

Since data is the fuel that drives machine learning models, and access to labeled data is generally expensive, semi-supervised methods are constantly popular. They enable the acquisition of large datasets without the need for too many expert labels. This work combines self-labeling techniques with active learning in a selective sampling scenario. We propose a new method that builds an ensemble classifier. Based on an evaluation of the inconsistency of the decisions of the individual base classifiers for a given observation, a decision is made on whether to request a new label or use the self-labeling. In preliminary studies, we show that naive application of self-labeling can harm performance by introducing bias towards selected classes and consequently lead to skewed class distribution. Hence, we also propose mechanisms to reduce this phenomenon. Experimental evaluation shows that the proposed method matches current selective sampling methods or achieves better results.