×

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

作者: M. B ×
换一批
01.
medRxiv (Medicine) 2026-06-12

The Acceptability of Three Co-Created Peer Support Interventions for People Living with Leprosy Reactions in Indonesia: A Mixed-Methods Pilot Study

Background: Leprosy reactions (LR) are immune-mediated complications associated with disability, emotional distress, and social isolation. We identified a gap in affected-individual-informed interventions that aim to improve the management of LR in healthcare settings. To address this gap, we assessed the acceptability of three peer-support interventions co-created with people affected by LR in Indonesia. Methods: Using an interactive learning and action approach, we co-created peer counselling, telesupport groups, and participatory video interventions which were piloted in an urban hospital and 13 rural community clinics. A mixed-methods design was applied with interviews, focus group discussions, and pre-post assessments involving four participant groups. Data were analyzed thematically using an acceptability framework. Results: One hundred participants were enrolled, and 92 completed the pilot intervention between November 2022 and July 2023. Qualitative findings showed that all interventions were acceptable. Peer counselling provided emotional reassurance through shared experiences and was perceived as trustworthy and supportive. Perceived burdens differed by setting, with time constraints in urban facilities and geographical barriers in rural clinics. Knowledge improved significantly among participants of peer counselling and telesupport groups in rural settings. Telesupport groups facilitated connection, information exchange, and continuity of care. Digital access and literacy limited participation for some, particularly in rural areas. The participatory video was perceived as reassuring and informative. Improvements in knowledge, attitude, practices, and mental well-being domain scores were observed among urban participants, but responses in rural settings showed less change. Participants and co-implementers reported increased self-efficacy, participants confidence to perform required behaviors within peer support interventions, with effects shaped by intervention and setting. Conclusions: The three co-created peer-support interventions were acceptable for individuals with LR in diverse healthcare settings. These outcomes highlight the importance and effectiveness of selective, and context-sensitive implementation of one or more peer-support modalities.

02.
medRxiv (Medicine) 2026-06-22

A Plasmodium vivax controlled human infection and transmission model to evaluate interventions across the life cycle

Background Plasmodium vivax is an underappreciated cause of malaria disease burden. No reproducible and standardized full life-cycle controlled human malaria infection (CHMI) model to accelerate development of novel interventions is available. Methods This transmission-CHMI trial was conducted in Nijmegen, Netherlands. Healthy, malaria-naive adults were sequentially enrolled into three cohorts of four and inoculated with the asexual blood-stage isolate PvW1. Primary endpoint was proportion of oocyst-positive laboratory-reared Anopheles stephensi mosquitoes. The sequential design allowed for adaptations between cohorts. At parasitemia >10 parasites/microL or symptom onset, participants received oral gametocyte-sparing treatment (GST): mepacrine (Cohort 1 and 3; 100 mg at 0, 8 16 hours, then once daily for 3 days) or piperaquine (Cohort 3; 480 mg single-dose). Transmission was assessed by direct skin feeding (DSF) and membrane feeding assay (DMFA) with and without enrichment of gametocytes. End-of-study treatment was atovaquone-proguanil (1000/400 mg once daily for 3 days). The trial was registered: NL-OMON57011. Findings Participants were enrolled between September 17, 2024 and March 25, 2025, all (12/12) developed parasitemia and transmitted PvW1 to mosquitoes. No serious adverse events occurred. Most adverse reactions were related to malaria. Mepacrine and piperaquine reduced asexual parasitemia while preserving gametocytemia and transmission. Peak transmission occurred within 3 days after GST and depended on the parasite developmental cycle, with highest gametocyte-infectivity ~48 h post ring-stage. In Cohort 3, mosquito infection reached 100% in all transmission assays. Median peak oocyst counts were 24 (IQR: 14-31) for DSF, 17 (12-19) for DMFA, and 150 (116-199) for enriched DMFA. A two-fold increase in pre-GST maximal parasitemia was associated with 20 additional oocysts (95% CI 8,6-32) in enriched DMFA. Sporozoites were viable in primary human hepatocytes. Interpretation A PvW1 transmission-CHMI is reproducible and safe, enabling P. vivax sporozoite production, relapse models and evaluation of transmission-blocking interventions.

03.
bioRxiv (Bioinfo) 2026-06-22

Benchmarking cell type annotation in spatial transcriptomics: resolving cellular hierarchies, biological fidelity, and dynamic cell states

Spatial transcriptomics enables the quantification of gene expression within its native tissue context, providing unprecedented insight into tissue architecture, cellular ecosystems, and local cell-cell interactions at regional and single-cell resolution. Accurate cell type annotation is a critical prerequisite for interpreting these data and is often the first and most essential step in downstream analysis. Despite rapid advances in computational methods, cell type annotation remains challenging and frequently requires extensive expert-driven manual curation based on marker-gene expression, spatial context, and prior biological knowledge. While early approaches relied primarily on transcriptional similarity, newer methods increasingly incorporate spatial information, histological features, and multimodal data to improve annotation accuracy. Nevertheless, reliable annotation remains difficult when biological interpretation requires fine-grained subtype resolution, particularly for platforms with limited gene panels, tissues undergoing dynamic cellular state transitions, and studies in which reference and query datasets differ substantially in biological context or technical modality. Here, we present a systematic benchmark of 20 state-of-the-art cell type annotation methods across four spatial transcriptomics datasets spanning diverse technologies, experimental conditions, cell numbers, and gene panel sizes. Importantly, all benchmark datasets contain expert-curated cell type labels, including well-resolved cell populations and subtype annotations, providing high-quality biological ground truth for evaluation. The benchmark encompasses both reference-based and reference-free methods representing a broad range of computational frameworks. Performance was assessed using conventional classification metrics, including accuracy and F1-based measures, together with structure-aware metrics that evaluate both cell-level annotation accuracy and preservation of higher-order biological organization. Across datasets, annotation performance varied substantially according to tissue context, reference-query similarity, and annotation granularity. Fine-grained subtype annotation and recovery of rare cell populations remained challenging for many methods, particularly in datasets capturing injury, repair, developmental, and regenerative processes characterized by continuous cellular state transitions. Notably, high classification accuracy did not necessarily correspond to preservation of global cellular relationships or biologically coherent downstream pathway and gene-set enrichment analyses. Overall, scANVI, Seurat, and TACCO consistently ranked among the top-performing methods, although their relative advantages were context dependent. Together, our results provide a comprehensive assessment of current annotation strategies for spatial transcriptomics and offer practical guidance for selecting methods that best align with specific biological questions, dataset characteristics, and analytical priorities.

04.
arXiv (CS.CV) 2026-06-17

Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors

Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrated strong adaptability to natural images. However, extending their use to the medical domain, particularly for volumetric (3D) images, is challenging due to high computational complexity, volumetric dependencies and the semantic gap between visual features and clinical terminology. Naively fine-tuning LLMs on limited medical data often leads to overfitting and clinical hallucination, where linguistic fluency is prioritized over clinical factuality. In this study, we investigate parameter-efficient adaptation strategies for volumetric CT report generation and introduce RAD3D-Prefix, a lightweight diagnostic-prior conditioning framework that minimizes the need for extensive parameter training. This module integrates image embeddings with multi-label diagnostic classification logits, preserving critical clinical details while bridging the semantic gap. By keeping the LLM frozen, our method requires minimal trainable parameters and mitigates the risk of overfitting on small, domain-specific datasets. Through a systematic study spanning LLMs from 96.1M to 1.6B parameters, we find that fine-tuning is most beneficial for smaller LLMs, whereas freezing larger (~1B+ LLMs and training only lightweight projection layers provides a superior trade-off between performance, generalization, and computational efficiency. Across multiple automatic metrics and a clinical reader study, RAD3D-Prefix outperforms comparable parameter-efficient baselines and demonstrates strong out-of-domain generalization while using substantially fewer trainable parameters than fully fine-tuned alternatives.

05.
arXiv (CS.CL) 2026-06-24

Posterior Refinement: Fast Language Generation via Any-Order Flow Maps

Non-autoregressive generation offers a powerful paradigm for iterative refinement, allowing models to recursively critique, erase and regenerate arbitrary subsets of tokens. However, existing non-autoregressive models fail to realize this potential. Masked Diffusion Models (MDMs) suffer from factorization error, causing sample quality to collapse when generating multiple tokens simultaneously. Flow Map Language Models (FMLMs) circumvent this bottleneck via joint sequence transport for excellent few-step generation, but sacrifice the inference-time flexibility of MDMs. We introduce FMLM+, a framework that bridges this gap by equipping FMLM with masking-style noise schedules. While generating the full sequence in a single step, FMLM+ simultaneously scores the global consistency of each token a posteriori. We leverage this to introduce Posterior Refinement, a novel inference-time refinement strategy that enables the model to adaptively self-correct its outputs, matching the performance of discrete baselines with 32x fewer NFEs. Across diverse benchmarks, we demonstrate that FMLM+ with Posterior Refinement improves the speed–quality tradeoff over both MDM and FMLM families, providing a scalable foundation for high-fidelity language modeling.

06.
arXiv (CS.CL) 2026-06-15

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

07.
arXiv (quant-ph) 2026-06-19

Quantum-Accelerated Self-Consistent Field: A Hybrid Algorithm

arXiv:2606.20176v1 Announce Type: new Abstract: We present the Grover adaptive search self-consistent field (GAS-SCF) algorithm. GAS-SCF leverages quantum arithmetic to construct an efficient oracle that marks target states (Fock states) which improve upon some initial classical energy estimate. Amplitude amplification then increases the probability of measuring these states. This approach offers a theoretical quadratic speed-up for the optimization problem encountered in SCF quantum chemistry and establishes a baseline against which structured optimization algorithms, such as QAOA and DQI may be compared. In this work, we classically simulate three examples as proofs of concept of the algorithm, the largest consisting of 26 qubits. We then extend our analysis to two larger systems, with O3 representing the largest case at 330 qubits. These examples are chosen to probe classically challenging SCF regimes. Achieving chemically relevant applications of GAS-SCF will require large-scale, fault-tolerant quantum hardware.

08.
arXiv (CS.AI) 2026-06-16

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

arXiv:2603.15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues – where ML approaches fail – achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.

09.
medRxiv (Medicine) 2026-06-11

Allostatic Load in Endometrial Cancer Disparities

Background: Endometrial cancer incidence and mortality are increasing, particularly among Black women and for aggressive subtypes. Allostatic load (AL), a composite measure of physiologic dysregulation across metabolic, cardiovascular, and immune systems, varies by racial category and tumor subtype in other cancers. Endometrial cancer is strongly associated with obesity, and it is unknown whether AL scores maintain sufficient heterogeneity to evaluate differences across subgroups or with clinical outcomes. Objective: To describe the performance of AL scoring in endometrial cancer patients and examine associations with tumor characteristics (grade/histology) and survival outcomes. Methods: We evaluated AL among 398 participants newly diagnosed with endometrial cancer. AL score was calculated by assigning 1 point for each ''high-risk'' value (by clinical reference range or distribution-based) for 15 biologic variables for vital signs, anthropometrics, blood-based biomarkers, and medical comorbidities. Results: Distribution-based thresholds for variables were used to preserve heterogeneity in this obesity-dominant context. Overall, 68.7% of Black women had high AL compared to White (56.7%), Hispanic (56.7%), and other race (32.3%) women. Decision tree analyses revealed grade-dependent associations between AL and survival. For women with low-grade tumors, higher AL was associated with poorer overall survival. For high-grade tumors, intermediate AL ([≥]4,

10.
arXiv (CS.AI) 2026-06-16

Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems

arXiv:2606.16257v1 Announce Type: cross Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities is a fundamental challenge in machine learning, particularly when the exact gradient of the potential is unavailable and must be approximated via stochastic gradients that exhibit high variance under a fixed budget of gradient computations per iteration. Although variance reduction techniques such as SGD with momentum, STORM, and PAGE have demonstrated improved convergence properties in non-convex optimization, their implications for sampling from non-log-concave distributions remain largely unexplored. In this work, we develop the first unified analysis of these estimators for sampling from non-log-concave distributions. We establish improved non-asymptotic convergence rates in $\varepsilon$-relative Fisher information and, under a Poincaré inequality assumption, in squared total variation distance, and further prove weak convergence to the target distribution. We extend our analysis to solving inverse problems with score-based generative priors. We empirically validate our theory and demonstrate that, under a fixed gradient computations per iteration, variance-reduction techniques consistently improve sample quality in two standard imaging applications.

11.
arXiv (CS.CV) 2026-06-11

Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction

Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their presence in facial landmark detection remains unexplored. In this paper, we conduct a systematic audit of demographic bias in this task, analyzing the age, gender, and race biases. To this end, we introduce a controlled statistical methodology to disentangle demographic effects from confounding visual factors. Our analysis demonstrates that visual confounders, particularly head pose and face resolution, heavily outweigh the impact of demographic attributes. Notably, after accounting for these confounders, performance disparities across gender and race vanish. However, we identify a statistically significant age-related bias, with higher localization errors for older individuals. This shows that fairness issues can emerge even in low-level vision components and can propagate through the HRI pipeline. We argue that auditing and correcting such biases is a necessary step toward trustworthy and equitable robot perception systems.

12.
arXiv (CS.LG) 2026-06-24

A Differentially Private Weighted Empirical Risk Minimization Procedure and its Application to Outcome Weighted Learning

arXiv:2307.13127v3 Announce Type: replace-cross Abstract: Data used to train predictive models via empirical risk minimization (ERM) often contain sensitive personal information. While differential privacy (DP) provides mathematically provable bounds to protect such data, previous work has focused almost exclusively on unweighted ERM. We consider weighted ERM (wERM) – an important generalization where individual contributions to the objective function vary. We propose the first DP algorithm for general wERM with formal privacy guarantees and derive both its empirical and population excess risk bounds. Crucially, this general wERM framework provides a pathway for deriving privacy-preserving learning methods for individualized treatment rules, including the popular outcome-weighted learning (OWL) approach. We evaluate DP-wERM applied to OWL in simulated and real data experiments. Our empirical results demonstrate that training OWL models via wERM provides strong DP guarantees while maintaining robust performance, proving the method is practical for sensitive, real-world data.

13.
medRxiv (Medicine) 2026-06-22

A Controlled Human Malaria Infection model for relapsing Plasmodium vivax

Background Plasmodium vivax malaria relapses are a major source of morbidity and onward transmission of infection. The underlying mechanisms are poorly understood and current therapies sub-optimal. We examined the safety and feasibility of a controlled human malaria infection (CHMI) model for relapsing P. vivax. Methods We conducted an open-label, proof-of-concept, CHMI study of relapsing P. vivax. Healthy, malaria-naive, Duffy-positive adults aged 18-45 years with extensive CYP2D6 metaboliser phenotype and normal blood glucose-6-phosphate dehydrogenase (G6PD) levels were recruited in Oxford, UK. Mosquito-bite CHMI was performed in Nijmegen, The Netherlands, using Anopheles stephensi mosquitoes infected with PvW1, a clonal isolate of P. vivax from Thailand. All follow-up visits were conducted in Oxford, UK. Primary P. vivax infections (qPCR > 500 genome copies/mL) were treated with artemether-lumefantrine (80mg/480mg at 8, 24, 36, 48 and 60 hours). From Day 28 following CHMI, participants attended a fortnightly clinic for clinical review and qPCR blood sampling, with additional assessments performed for any reported symptoms. P. vivax relapse infections (qPCR > 500 genome copies/mL) were treated with artemether-lumefantrine as per primary infection. Definitive anti-malarial treatment with atovaquone-proguanil (1000mg/400mg once daily for three days) and primaquine (0{middle dot}5 mg/kg/day for 14 days) was administered six months following CHMI, regardless of parasitaemia or symptoms. The primary objective was to assess the safety, feasibility and frequency of relapsing P. vivax after CHMI. Remote follow-up (5 years) is ongoing. The study is registered with ISRCTN registry (ISRCTN48625883). Findings 20 participants were screened for eligibility from 21 January 2025. Five participants (median age 22 years) underwent CHMI (five infected mosquitoes per participant) on 15 April 2025. All participants developed primary P. vivax infection and experienced at least one relapse infection. Two participants experienced a second relapse. Overall incidence rate was 3{middle dot}6 relapse infections per person-year. Solicited adverse events were mild or moderate and there were no serious adverse events. Definitive anti-malarial treatment was administered to all participants. One participant experienced primaquine-induced methaemoglobinaemia, resolving with early discontinuation of treatment (total dose 5{middle dot}3 mg/kg). To date, more than six months after primaquine treatment, no further relapses have been recorded. Interpretation CHMI of relapsing P. vivax is safe and feasible, allowing exploration of the mechanisms underlying relapse infections and providing a platform for future anti-relapse efficacy studies. Funding European Union Horizon Europe programme and UK Research and Innovation (UKRI) via OptiVivax consortium; UK National Institute for Health and Care Research Biomedical Research Centre: Oxford; and UK Medical Research Council.

14.
medRxiv (Medicine) 2026-06-10

A Three-Tier Operational Benchmark for Evaluating Large Language Models on Hospital Medication Safety

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.

15.
arXiv (CS.AI) 2026-06-19

Review of Machine Learning Models for Solar Energetic Particle Prediction

arXiv:2606.19539v1 Announce Type: cross Abstract: Solar energetic particle (SEP) events have attracted increasing attention due to their significant radiation hazards for aviation, spacecraft electronics, and human missions beyond Earth's magnetosphere. From a scientific perspective, SEP events are intriguing because they arise from a set of physical processes extending from the solar surface and corona through the heliosphere, offering insight into particle acceleration and transport mechanisms that are widely applicable across astrophysics. Therefore, advancing our ability to understand and predict SEP events is essential both for deepening our knowledge of such mechanisms and for safeguarding space technologies and exploration. Traditionally, researchers have modeled SEPs using physics-based simulations and empirical methods. More recently, machine learning (ML) has emerged as a new tool for understanding and predicting SEP events. The purpose of this manuscript is to review the currently available ML models for SEP prediction, identify the datasets used for training, compare their architectures, inputs, and outputs, and, based on these insights, outline good practices and recommendations for future research.

16.
medRxiv (Medicine) 2026-06-15

Multi-domain AD risk burden and plasma biomarkers in cognitively unimpaired adults

Introduction: Alzheimer's disease (AD) pathology accumulates decades before symptom onset, yet how the cumulative effect of genetic, familial, and modifiable lifestyle risk burden jointly affects plasma biomarker levels and trajectories in cognitively unimpaired older adults remains unknown. Methods: We analyzed data from 261 participants in the PREVENT-AD cohort. A composite risk score integrating APOE e4 status, polygenic score, family history, and modifiable/lifestyle risk was examined against six plasma biomarkers using linear regression and linear mixed-effects models. Results: APOE e4 was the strongest predictor of plasma biomarker levels. Higher composite risk burden was associated with elevated ptau181, ptau217, ptau217/Ab42, and GFAP levels, and lower Ab42/40 levels. A higher risk burden was predictive of accelerated ptau181 accumulation. Discussion: Cumulative AD risk burden is broadly associated with plasma biomarker levels and specifically predicts accelerated ptau181 accumulation in cognitively unimpaired older adults, supporting structured composite risk profiling as a framework for AD risk stratification.

17.
medRxiv (Medicine) 2026-06-19

Hyperleukocytosis and outcomes in pediatric B-cell acute lymphoblastic leukemia: A report from the REDIAL Consortium

Hyperleukocytosis (white blood cell [WBC] count >100 000/uL) at diagnosis is an important prognostic risk factor in pediatric acute lymphoblastic leukemia (ALL), though its significance with contemporary therapy is unclear. We analyzed 1 826 pediatric ALL patients from a multi-institution cohort to determine whether hyperleukocytosis independently predicts outcomes using multivariable Cox proportional hazard modeling. Hyperleukocytosis occurred in 211 patients (12%), with 121 having B-ALL, and showed no prognostic significance in T-ALL patients. In B-ALL, 5-year event-free survival (EFS) was 65% versus 89% for non-hyperleukocytosis patients, and overall survival (OS) was 78% versus 93%. After adjustment for age, cytogenetic risk, central nervous system disease status, and treatment site, hyperleukocytosis remained an independent predictor of end-of-induction minimal residual disease (MRD) positivity (odds ratio 2.53 [95% confidence interval [CI]: 1.71-3.94; p

18.
arXiv (CS.AI) 2026-06-17

First, do NOHARM: towards clinically safe large language models

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.