arXiv:2601.08005v1 Announce Type: new Abstract: Frontier AI regulations primarily focus on systems deployed to external users, where deployment is more visible and subject to outside scrutiny. However, high-stakes applications can occur internally when companies deploy highly capable systems within their own organizations, such as for automating R\&D, accelerating critical business processes, and handling sensitive proprietary data. This paper examines how frontier AI regulations in the United States and European Union in 2025 handle internal deployment. We identify three gaps that could cause internally-deployed systems to evade intended oversight: (1) scope ambiguity that allows internal systems to evade regulatory obligations, (2) point-in-time compliance assessments that fail to capture the continuous evolution of internal systems, and (3) information asymmetries that subvert regulatory awareness and oversight. We then analyze why these gaps persist, examining tensions around measurability, incentives, and information access. Finally, we map potential approaches to address them and their associated tradeoffs. By understanding these patterns, we hope that policy choices around internally deployed AI systems can be made deliberately rather than incidentally.

arXiv:2601.08333v1 Announce Type: new Abstract: LLM-based agent architectures systematically conflate information transport mechanisms with epistemic justification mechanisms. We formalize this class of architectural failures as semantic laundering: a pattern where propositions with absent or weak warrant are accepted by the system as admissible by crossing architecturally trusted interfaces. We show that semantic laundering constitutes an architectural realization of the Gettier problem: propositions acquire high epistemic status without a connection between their justification and what makes them true. Unlike classical Gettier cases, this effect is not accidental; it is architecturally determined and systematically reproducible. The central result is the Theorem of Inevitable Self-Licensing: under standard architectural assumptions, circular epistemic justification cannot be eliminated. We introduce the Warrant Erosion Principle as the fundamental explanation for this effect and show that scaling, model improvement, and LLM-as-judge schemes are structurally incapable of eliminating a problem that exists at the type level.

arXiv:2601.08559v1 Announce Type: new Abstract: Sustainable water resource management in transboundary river basins is challenged by fragmented data, limited real-time access, and the complexity of integrating diverse information sources. This paper presents WaterCopilot-an AI-driven virtual assistant developed through collaboration between the International Water Management Institute (IWMI) and Microsoft Research for the Limpopo River Basin (LRB) to bridge these gaps through a unified, interactive platform. Built on Retrieval-Augmented Generation (RAG) and tool-calling architectures, WaterCopilot integrates static policy documents and real-time hydrological data via two custom plugins: the iwmi-doc-plugin, which enables semantic search over indexed documents using Azure AI Search, and the iwmi-api-plugin, which queries live databases to deliver dynamic insights such as environmental-flow alerts, rainfall trends, reservoir levels, water accounting, and irrigation data. The system features guided multilingual interactions (English, Portuguese, French), transparent source referencing, automated calculations, and visualization capabilities. Evaluated using the RAGAS framework, WaterCopilot achieves an overall score of 0.8043, with high answer relevancy (0.8571) and context precision (0.8009). Key innovations include automated threshold-based alerts, integration with the LRB Digital Twin, and a scalable deployment pipeline hosted on AWS. While limitations in processing non-English technical documents and API latency remain, WaterCopilot establishes a replicable AI-augmented framework for enhancing water governance in data-scarce, transboundary contexts. The study demonstrates the potential of this AI assistant to support informed, timely decision-making and strengthen water security in complex river basins.

arXiv:2601.08673v1 Announce Type: new Abstract: Recent reports of large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency. We argue that this interpretation rests on a conceptual error. LLMs do not reason morally; they statistically internalize the record of human social interaction, including laws, contracts, negotiations, conflicts, and coercive arrangements. Behaviors commonly labeled as unethical or anomalous are therefore better understood as structural generalizations of interaction regimes that arise under extreme asymmetries of power, information, or constraint. Drawing on relational models theory, we show that practices such as blackmail are not categorical deviations from normal social behavior, but limiting cases within the same continuum that includes market pricing, authority relations, and ultimatum bargaining. The surprise elicited by such outputs reflects an anthropomorphic expectation that intelligence should reproduce only socially sanctioned behavior, rather than the full statistical landscape of behaviors humans themselves enact. Because human morality is plural, context-dependent, and historically contingent, the notion of a universally moral artificial intelligence is ill-defined. We therefore reframe concerns about artificial general intelligence (AGI). The primary risk is not adversarial intent, but AGI's role as an endogenous amplifier of human intelligence, power, and contradiction. By eliminating longstanding cognitive and institutional frictions, AGI compresses timescales and removes the historical margin of error that has allowed inconsistent values and governance regimes to persist without collapse. Alignment failure is thus structural, not accidental, and requires governance approaches that address amplification, complexity, and regime stability rather than model-level intent alone.

arXiv:2601.08690v1 Announce Type: new Abstract: Conversational AI is starting to support real clinical work, but most evaluation methods miss how compliance depends on the full course of a conversation. We introduce Obligatory-Information Phase Structured Compliance Evaluation (OIP-SCE), an evaluation method that checks whether every required clinical obligation is met, in the right order, with clear evidence for clinicians to review. This makes complex rules practical and auditable, helping close the gap between technical progress and what healthcare actually needs. We demonstrate the method in two case studies (respiratory history, benefits verification) and show how phase-level evidence turns policy into shared, actionable steps. By giving clinicians control over what to check and engineers a clear specification to implement, OIP-SCE provides a single, auditable evaluation surface that aligns AI capability with clinical workflow and supports routine, safe use.

arXiv:2601.07871v1 Announce Type: cross Abstract: Cardiovascular disease arises from interactions between inherited risk, molecular programmes, and tissue-scale remodelling that are observed clinically through imaging. Health systems now routinely generate large volumes of cardiac MRI, CT and echocardiography together with bulk, single-cell and spatial transcriptomics, yet these data are still analysed in separate pipelines. This review examines joint representations that link cardiac imaging phenotypes to transcriptomic and spatially resolved molecular states. An imaging-anchored perspective is adopted in which echocardiography, cardiac MRI and CT define a spatial phenotype of the heart, and bulk, single-cell and spatial transcriptomics provide cell-type- and location-specific molecular context. The biological and technical characteristics of these modalities are first summarised, and representation-learning strategies for each are outlined. Multimodal fusion approaches are reviewed, with emphasis on handling missing data, limited sample size, and batch effects. Finally, integrative pipelines for radiogenomics, spatial molecular alignment, and image-based prediction of gene expression are discussed, together with common failure modes, practical considerations, and open challenges. Spatial multiomics of human myocardium and atherosclerotic plaque, single-cell and spatial foundation models, and multimodal medical foundation models are collectively bringing imaging-anchored multiomics closer to large-scale cardiovascular translation.

arXiv:2601.08183v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show promise in gastroenterology, yet their performance against comprehensive clinical workflows and human benchmarks remains unverified. To systematically evaluate state-of-the-art MLLMs across a panoramic gastrointestinal endoscopy workflow and determine their clinical utility compared with human endoscopists. We constructed GI-Bench, a benchmark encompassing 20 fine-grained lesion categories. Twelve MLLMs were evaluated across a five-stage clinical workflow: anatomical localization, lesion identification, diagnosis, findings description, and management. Model performance was benchmarked against three junior endoscopists and three residency trainees using Macro-F1, mean Intersection-over-Union (mIoU), and multi-dimensional Likert scale. Gemini-3-Pro achieved state-of-the-art performance. In diagnostic reasoning, top-tier models (Macro-F1 0.641) outperformed trainees (0.492) and rivaled junior endoscopists (0.727; p>0.05). However, a critical "spatial grounding bottleneck" persisted; human lesion localization (mIoU >0.506) significantly outperformed the best model (0.345; p

arXiv:2601.08634v1 Announce Type: cross Abstract: While recent research has systematically documented political orientation in large language models (LLMs), existing evaluations rely primarily on direct probing or demographic persona engineering to surface ideological biases. In social psychology, however, political ideology is also understood as a downstream consequence of fundamental moral intuitions. In this work, we investigate the causal relationship between moral values and political positioning by treating moral orientation as a controllable condition. Rather than simply assigning a demographic persona, we condition models to endorse or reject specific moral values and evaluate the resulting shifts on their political orientations, using the Political Compass Test. By treating moral values as lenses, we observe how moral conditioning actively steers model trajectories across economic and social dimensions. Our findings show that such conditioning induces pronounced, value-specific shifts in models' political coordinates. We further notice that these effects are systematically modulated by role framing and model scale, and are robust across alternative assessment instruments instantiating the same moral value. This highlights that effective alignment requires anchoring political assessments within the context of broader social values including morality, paving the way for more socially grounded alignment techniques.

arXiv:2601.08732v1 Announce Type: cross Abstract: Accurate delineation of acute ischemic stroke lesions in MRI is a key component of stroke diagnosis and management. In recent years, deep learning models have been successfully applied to the automatic segmentation of such lesions. While most proposed architectures are based on the U-Net framework, they primarily differ in their choice of loss functions and in the use of deep supervision, residual connections, and attention mechanisms. Moreover, many implementations are not publicly available, and the optimal configuration for acute ischemic stroke (AIS) lesion segmentation remains unclear. In this work, we introduce ISLA (Ischemic Stroke Lesion Analyzer), a new deep learning model for AIS lesion segmentation from diffusion MRI, trained on three multicenter databases totaling more than 1500 AIS participants. Through systematic optimization of the loss function, convolutional architecture, deep supervision, and attention mechanisms, we developed a robust segmentation framework. We further investigated unsupervised domain adaptation to improve generalization to an external clinical dataset. ISLA outperformed two state-of-the-art approaches for AIS lesion segmentation on an external test set. Codes and trained models will be made publicly available to facilitate reuse and reproducibility.

arXiv:2509.14507v2 Announce Type: replace Abstract: Natural Language to SQL (NL2SQL) provides a new model-centric paradigm that simplifies database access for non-technical users by converting natural language queries into SQL commands. Recent advancements, particularly those integrating Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) reasoning, have made significant strides in enhancing NL2SQL performance. However, challenges such as inaccurate task decomposition and keyword extraction by LLMs remain major bottlenecks, often leading to errors in SQL generation. While existing datasets aim to mitigate these issues by fine-tuning models, they struggle with over-fragmentation of tasks and lack of domain-specific keyword annotations, limiting their effectiveness. To address these limitations, we present DeKeyNLU, a novel dataset which contains 1,500 meticulously annotated QA pairs aimed at refining task decomposition and enhancing keyword extraction precision for the RAG pipeline. Fine-tuned with DeKeyNLU, we propose DeKeySQL, a RAG-based NL2SQL pipeline that employs three distinct modules for user question understanding, entity retrieval, and generation to improve SQL generation accuracy. We benchmarked multiple model configurations within DeKeySQL RAG pipeline. Experimental results demonstrate that fine-tuning with DeKeyNLU significantly improves SQL generation accuracy on both BIRD (62.31% to 69.10%) and Spider (84.2% to 88.7%) dev datasets.

arXiv:2512.20387v4 Announce Type: replace Abstract: We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and natural-language prompts, enabling cross-modal reasoning for industrial simulation systems. To support this new paradigm, the study constructs the first large-scale dataset for generative digital twins, comprising over 120,000 prompt-sketch-code triplets that enable multimodal learning between textual descriptions, spatial structures, and simulation logic. In parallel, three novel evaluation metrics, Structural Validity Rate (SVR), Parameter Match Rate (PMR), and Execution Success Rate (ESR), are proposed specifically for this task to comprehensively evaluate structural integrity, parameter fidelity, and simulator executability. Through systematic ablation across vision encoders, connectors, and code-pretrained language backbones, the proposed models achieve near-perfect structural accuracy and high execution robustness. This work establishes a foundation for generative digital twins that integrate visual reasoning and language understanding into executable industrial simulation systems. Project page: https://danielhsu2014.github.io/GDT-VLSM-project/

arXiv:2405.16041v4 Announce Type: replace-cross Abstract: Providing explainable molecular property predictions is critical for many scientific domains, such as drug discovery and material science. Though transformer-based language models have shown great potential in accurate molecular property prediction, they neither provide chemically meaningful explanations nor faithfully reveal the molecular structure-property relationships. In this work, we develop a framework for explainable molecular property prediction based on language models, dubbed as Lamole, which can provide chemical concepts-aligned explanations. We take a string-based molecular representation -- Group SELFIES -- as input tokens to pretrain and fine-tune our Lamole, as it provides chemically meaningful semantics. By disentangling the information flows of Lamole, we propose combining self-attention weights and gradients for better quantification of each chemically meaningful substructure's impact on the model's output. To make the explanations more faithfully respect the structure-property relationship, we then carefully craft a marginal loss to explicitly optimize the explanations to be able to align with the chemists' annotations. We bridge the manifold hypothesis with the elaborated marginal loss to prove that the loss can align the explanations with the tangent space of the data manifold, leading to concept-aligned explanations. Experimental results over six mutagenicity datasets and one hepatotoxicity dataset demonstrate Lamole can achieve comparable classification accuracy and boost the explanation accuracy by up to 14.3%, being the state-of-the-art in explainable molecular property prediction.

arXiv:2504.08526v2 Announce Type: replace-cross Abstract: Generative AI increasingly supports scientific inference, from protein structure prediction to weather forecasting. Yet its distinctive failure mode, hallucination, raises epistemic alarm bells. I argue that this failure mode can be addressed by shifting from data-centric to phenomenon-centric assessment. Through case studies of AlphaFold and GenCast, I show how scientific workflows discipline generative models through theory-guided training and confidence-based error screening. These strategies convert hallucination from an unmanageable epistemic threat into bounded risk. When embedded in such workflows, generative models support reliable inference despite opacity, provided they operate in theoretically mature domains.

arXiv:2505.07917v2 Announce Type: replace-cross Abstract: Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines a Retrieval-Augmented Generation (RAG) system for biomedical QA, evaluating retrieval strategies and response time trade-offs. We first assess state-of-the-art retrieval methods, including BM25, BioBERT, MedCPT, and a hybrid approach, alongside common data stores such as Elasticsearch, MongoDB, and FAISS, on a ~10% subset of PubMed (2.4M documents) to measure indexing efficiency, retrieval latency, and retriever performance in the end-to-end RAG system. Based on these insights, we deploy the final RAG system on the full 24M PubMed corpus, comparing different retrievers' impact on overall performance. Evaluations of the retrieval depth show that retrieving 50 documents with BM25 before reranking with MedCPT optimally balances accuracy (0.90), recall (0.90), and response time (1.91s). BM25 retrieval time remains stable (82ms), while MedCPT incurs the main computational cost. These results highlight previously not well-known trade-offs in retrieval depth, efficiency, and scalability for biomedical QA. With open-source code, the system is fully reproducible and extensible.

arXiv:2505.13565v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) poses both significant risks and valuable opportunities for democratic governance. This paper introduces a dual taxonomy to evaluate AI's complex relationship with democracy: the AI Risks to Democracy (AIRD) taxonomy, which identifies how AI can undermine core democratic principles such as autonomy, fairness, and trust; and the AI's Positive Contributions to Democracy (AIPD) taxonomy, which highlights AI's potential to enhance transparency, participation, efficiency, and evidence-based policymaking. Grounded in the European Union's approach to ethical AI governance, and particularly the seven Trustworthy AI requirements proposed by the European Commission's High-Level Expert Group on AI, each identified risk is aligned with mitigation strategies based on EU regulatory and normative frameworks. Our analysis underscores the transversal importance of transparency and societal well-being across all risk categories and offers a structured lens for aligning AI systems with democratic values. By integrating democratic theory with practical governance tools, this paper offers a normative and actionable framework to guide research, regulation, and institutional design to support trustworthy, democratic AI. It provides scholars with a conceptual foundation to evaluate the democratic implications of AI, equips policymakers with structured criteria for ethical oversight, and helps technologists align system design with democratic principles. In doing so, it bridges the gap between ethical aspirations and operational realities, laying the groundwork for more inclusive, accountable, and resilient democratic systems in the algorithmic age.

arXiv:2510.06780v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) encode substantial factual knowledge, yet measuring and systematizing this knowledge remains challenging. Converting it into structured format, for example through recursive extraction approaches such as the GPTKB methodology (Hu et al., 2025b), is still underexplored. Key open questions include whether such extraction can terminate, whether its outputs are reproducible, and how robust they are to variations. We systematically study LLM knowledge materialization using miniGPTKBs (domain-specific, tractable subcrawls), analyzing termination, reproducibility, and robustness across three categories of metrics: yield, lexical similarity, and semantic similarity. We experiment with four variations (seed, language, randomness, model) and three illustrative domains (from history, entertainment, and finance). Our findings show (i) high termination rates, though model-dependent; (ii) mixed reproducibility; and (iii) robustness that varies by perturbation type: high for seeds and temperature, lower for languages and models. These results suggest that LLM knowledge materialization can reliably surface core knowledge, while also revealing important limitations.

This is the online version of The Readout, STAT’s flagship biotech newsletter. Sign up to get it in your inbox.

You’re back. We’re sort of back. It’s Day 2 of JPM and we’re definitely not exhausted or delirious yet.

This is Elaine Chen, Adam Feuerstein, Matt Herper, and Allison DeAngelis again. We’ve got a lot more news today, so let’s get to it.

The next test for Kite Pharma — and Gilead

It’s anito-cel, the CAR-T therapy for multiple myeloma that Gilead is developing in partnership with Arcellx. Gilead submitted the therapy to the FDA sometime before the end of December, Cindy Perettie, executive vice president of Kite Pharma, the cell therapy division of Gilead, told STAT at a Gilead media breakfast.

Continue to STAT+ to read the full story…

© Alex Hogan/STAT

The tech giant has pledged to be a "good neighbor" as it continues to invest in AI infrastructure throughout the country.

Background: The global rise of metabolic associated fatty liver disease (MAFLD) reflects the urgent need for accurate, non-invasive diagnostic approaches. The invasive nature of liver biopsy and the limited sensitivity of ultrasound (US) in detecting early steatosis highlight a critical diagnostic gap. Artificial intelligence (AI) has emerged as a transformative tool, enabling the automated detection and grading of hepatic steatosis (HS) from medical imaging data. Objective: This systematic review and meta-analysis endeavors to quantitatively evaluate the diagnostic performance of AI models for HS, to comprehensively explore sources of inter-study heterogeneity, and to provide an in-depth appraisal of their clinical applicability, translational potential, and the major barriers impeding widespread implementation. Methods: PubMed, Cochrane Library, Embase, Web of Science, and IEEE Xplore databases were searched until September 24, 2025. Studies employing AI for the diagnosis of HS were included if they met the predefined PIRT framework and provided sufficient extractable data. Diagnostic performance indicators, including sensitivity, specificity, and the area under the summary receiver operating characteristic (SROC) curve (AUC), were extracted and quantitatively synthesized. Meta-analyses were conducted using a bivariate random-effects model. The methodological quality and risk of bias of the included studies were evaluated using the QUADAS-2 tool. Heterogeneity was comprehensively assessed through the I² statistic, bivariate boxplots, 95% prediction intervals (PIs), and threshold effect analysis. The clinical applicability of the diagnostic models was further examined using Fagan’s nomogram and likelihood ratio tests. Results: 36 eligible studies were identified, of which 33 (comprising 62 cohorts) were included in the quantitative synthesis. Pooled estimates demonstrated excellent diagnostic accuracy of AI models, with a summary sensitivity of 0.95 (95% CI: 0.93–0.96), specificity of 0.93 (95% CI: 0.91–0.94), and an AUC of 0.98 (95% CI: 0.96–0.99). Clinical applicability analysis (LR+ >10, LR– 75%). According to QUADAS-2, a high risk of bias, particularly in the Patient Selection domain (44.4%), may have contributed to the overestimation of real-world performance. Subgroup analyses showed that deep learning (DL) models significantly outperformed traditional machine learning (ML) approaches (AUC: 0.98 vs. 0.94). Models using US or histopathology as reference standards both achieved high diagnostic accuracy (AUC: 0.98). Retrospective design (AUC: 0.98), transfer learning (TL), and the use of public datasets (AUC: 0.99) were associated with superior performance but also contributed to inter-study heterogeneity. Conclusions: AI demonstrates remarkable potential for noninvasive screening and assessment of HS, especially in primary care. Nonetheless, clinical translation remains limited by substantial performance variability, predominance of retrospective designs, lack of rigorous external validation, and practical barriers such as data privacy and workflow integration. Future studies should prioritize prospective multicenter trials, standardized development pipelines, and robust external validation to bridge the gap between current evidence and clinical application. The key innovation of this review lies in establishing a unified, modality-agnostic analytical framework that integrates evidence beyond single-modality evaluations

Google has released Conductor, a new preview extension for Gemini CLI that introduces a structured, context-driven approach to AI-assisted software development. The extension is designed to address a common limitation of chat-based coding tools: the loss of project context across sessions.

By Robert Krzaczyński