arXiv:2609.12388v1 Announce Type: cross Abstract: Hidden debonding behind exterior ceramic tiles is a falling-tile hazard, and millimeter-wave radar offers a non-contact way to find it. Conventional interpretation first reconstructs a range profile, so its reliability is bounded by the available bandwidth, yet bandwidth is what sets the cost, the acquisition time, and the regulatory footprint of a deployed system. This work asks whether that bandwidth can be traded for computation. A 4-40 GHz stepped-frequency system scans twelve exterior-wall specimens containing 0.5-1.0 mm air voids at different depths and interfaces, and the bandwidth dependence of A-scan, B-scan, and C-scan interpretation is analyzed to establish the resolution bound. RF-VoID is then proposed, which decides directly on the narrowband complex response: the sub-band is kept in its measured frequency order with amplitude and phase alongside the in-phase and quadrature channels, a dual-branch encoder reads it along the physical frequency axis using relative position encoding and a distance-dependent locality bias, and an inspection-oriented objective handles the class imbalance and the asymmetric error cost of facade screening. Under a mixed-sample protocol the method attains 98.61% accuracy and a 95.84% F1-score with 0.5 GHz of bandwidth, a seventy-two-fold reduction relative to the full sweep, without range-profile reconstruction, deconvolution, or depth-slice selection; on specimens held out entirely from training it remains the strongest of the compared models, with a mean macro F1-score of 62.12% at 0.5 GHz that rises to 68.57% at 1 GHz.

arXiv:2605.23958v1 Announce Type: cross Abstract: M365 Copilot is used every week by millions of people across more than a million companies around the world as part of their workflows. Uniquely positioned in the AI landscape given its near-exclusive use for work purposes, M365 Copilot can offer a clear picture of how people use AI for work and where that usage may expand next. This paper characterizes that usage through direct classification of user interactions with M365 Copilot Chat. Based on an anonymized and privacy-preserving analysis of a sample of approximately 5.5 million sessions, we combine a learned classification of user intent with a classification of O*NET work activities done with M365 Copilot Chat. We find that M365 Copilot is emerging as an everyday assistant for knowledge work: writing dominates, but users also rely on it for information retrieval, analysis, decision making and strategizing, and evaluating and diagnosing programs and systems, among others. Information seeking tasks remain common, but time trends suggest a relative shift away from ``chat as search'' and toward content and communication-related work. Comparisons across occupational groupings and to work done in the labor market further show that usage is broad but uneven, where the relative share of work done with M365 Copilot Chat cuts across jobs in some cases and is occupation-specific in others. Areas of relative underrepresentation in the labor market suggest the next frontier for enterprise AI adoption.

arXiv:2602.17234v2 Announce Type: replace Abstract: Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledge. We introduce a claim-level evaluation framework that decomposes prediction rationales into atomic claims and applies Shapley values to quantify each claim's decision impact, yielding \textbf{Shapley-DCLR} (\textbf{Shapley}-weighted \textbf{D}ecision-\textbf{C}ritical \textbf{L}eakage \textbf{R}ate) -- an interpretable metric measuring what fraction of decision-driving reasoning is contaminated. We further propose \textbf{TimeSPEC} (\textbf{Time}-\textbf{S}upervised \textbf{P}rediction with \textbf{E}xtracted \textbf{C}laims), an inference-time architecture that interleaves temporally-filtered retrieval with claim-level supervision, producing predictions grounded entirely in pre-cutoff evidence. Across three LLMs, the ablation experiments confirm retrieval and supervision are jointly necessary; and a three-task probe further illstrates that the performance cost of temporal enforcement scales with each task's reliance on post-cutoff information.

arXiv:2505.21605v3 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SoSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SoSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 84.9% for Deepseek-R1 and 50.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

arXiv:2508.10703v3 Announce Type: replace Abstract: Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in the biomedical domain which contains numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large language model (LLM)-based ontology alignment framework, which enriches the semantic representations of ontology concepts via generating textual definitions, retrieves alignment candidates with an embedding model, and incorporates exact matching-based tools to improve precision. Extensive experiments conducted on the OAEI Bio-ML track demonstrate that GenOM can often achieve competitive performance, surpassing many baselines including traditional OM systems and recent LLM-based methods. Further ablation studies confirm the effectiveness of semantic enrichment and few-shot prompting, highlighting the framework's robustness and adaptability.

arXiv:2603.03672v1 Announce Type: cross Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a structural property of modern predictors: for a given test instance, only a small subset of training points influences the prediction. We formalize this model-induced locality through support sets defined by the model's computational pathway (e.g., neighbors in KNN, leaves in trees, receptive fields in GNNs), showing that Shapley computation can be projected onto these supports without loss when locality is exact. This reframes Shapley evaluation as a structured data processing problem over overlapping support-induced subset families rather than exhaustive coalition enumeration. We prove that the intrinsic complexity of Local Shapley is governed by the number of distinct influential subsets, establishing an information-theoretic lower bound on retraining operations. Guided by this result, we propose LSMR (Local Shapley via Model Reuse), an optimal subset-centric algorithm that trains each influential subset exactly once via support mapping and pivot scheduling. For larger supports, we develop LSMR-A, a reuse-aware Monte Carlo estimator that remains unbiased with exponential concentration, with runtime determined by the number of distinct sampled subsets rather than total draws. Experiments across multiple model families demonstrate substantial retraining reductions and speedups while preserving high valuation fidelity.

arXiv:2602.14697v2 Announce Type: replace Abstract: Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving model contexts and model weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel. It applies RL updates to LLM weights conditioned on system prompts, and evolutionary updates to system prompts via mutation and crossover, two genetic operators based on LLM self-reflection. Each system prompt is assigned a TrueSkill rating for evolutionary selection, updated from relative performance within each RL iteration. E-SPL encourages a natural division between declarative knowledge encoded in prompts and procedural knowledge encoded in weights, resulting in improved performance across reasoning and agentic tasks. For instance, in an easy-to-hard (AIME $\rightarrow$ BeyondAIME) generalization setting, E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1% while also outperforming reflective prompt evolution (40.0%). Overall, our results demonstrate that RL and evolutionary prompt search are deeply synergistic, and unifying the two yields consistent gains in sample efficiency and generalization. Code: https://github.com/LunjunZhang/E-SPL