Imagen de Portada

Clinician input steers frontier AI models toward both accurate and harmful decisions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lopez, Ivan, Everett, Selin S., Bunning, Bryan J., Liang, April S., Yao, Dong Han, Vedak, Shivam C., Black, Kameron C., Ostmeier, Sophie, Ma, Stephen P., Alsentzer, Emily, Chen, Jonathan H., Chaudhari, Akshay S., Horvitz, Eric
Formato:	Preprint
Publicado:	2026
Materias:	Human-Computer Interaction Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
por: Varma, Maya, et al.
Publicado: (2025)

LieRE: Lie Rotational Positional Encodings
por: Ostmeier, Sophie, et al.
Publicado: (2024)

Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
por: Chen, Wenyuan, et al.
Publicado: (2025)

Attention Head Entropy of LLMs Predicts Answer Correctness
por: Ostmeier, Sophie, et al.
Publicado: (2026)

Die Konvergenzkriterien des Maastricht-Vertrages
por: Bünning, Lars
Publicado: (2020)

PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
por: Liu, Ruoqi, et al.
Publicado: (2026)

Oekologieorientierte Produktinnovationen
por: Ostmeier, Hanns
Publicado: (2019)

Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
por: Kung, Gustavo Chau Loo, et al.
Publicado: (2026)

When accurate prediction models yield harmful self-fulfilling prophecies
por: van Amsterdam, Wouter A. C., et al.
Publicado: (2023)

Use of the correlation between input variables in estimating the risk of feedlot finishing of steers and young steers
por: PAULO S. PACHECO
Publicado: (2014)

Topologically noise robust network steering without inputs
por: Baheti, Dhruv, et al.
Publicado: (2025)

Understanding Perspectives of Patients, Caregivers and Clinicians towards Emerging Collaborative-decision Making Technologies
por: Chung, Ray-Yuan, et al.
Publicado: (2026)

MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
por: Varma, Maya, et al.
Publicado: (2025)

Effect of ants and an ant-tended herbivore on seed production of a neotropical herb
por: Horvitz C. C. And Schemske W
Publicado: (1984)

Flame retardant, hexabromocyclododecane, increases production of pro‐inflammatory cytokines, interleukin 1‐beta and interleukin 6, in human immune cells
por: April Falconer‐Turner, et al.
Publicado: (2024)

Reflection Comics: Draw Attention to Intercultural Communication in Context
por: Lucy Bunning, et al.
Publicado: (2025)

Increases in salinity variability harm both oysters and their predators, offsetting predicted effects on population dynamics
por: Christian J. C. Commander, et al.
Publicado: (2025)

Increases in salinity variability harm both oysters and their predators, offsetting predicted effects on population dynamics.
por: Commander, Christian J C, et al.
Publicado: (2026)

OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics
por: Gozlan, Yoni, et al.
Publicado: (2024)

GREEN: Generative Radiology Report Evaluation and Error Notation
por: Ostmeier, Sophie, et al.
Publicado: (2024)

Pollinator limitation, cost of reproduction, and fitness in plants : a transition-matrix demogrphic approach
por: Calvo, R.N. & Horvitz, C.C
Publicado: (1985)

Function regression using the forward forward training and inferring paradigm
por: Padmani, Shivam, et al.
Publicado: (2025)

Master Clinician Editorial
por: Leonard Tibbetts, et al.
Publicado: (2025)

CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
por: Hein, Dennis, et al.
Publicado: (2024)

Can Revealed Preferences Clarify LLM Alignment and Steering?
por: Yamin, Khurram, et al.
Publicado: (2026)

MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries
por: Grolleau, François, et al.
Publicado: (2025)

Efficient and accurate steering of Large Language Models through attention-guided feature learning
por: Davarmanesh, Parmida, et al.
Publicado: (2026)

Generalized two-point visual control model of human steering for accurate state estimation
por: Mai, Rene, et al.
Publicado: (2024)

From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis
por: Mottez, Clemence, et al.
Publicado: (2025)

Learning and steering game dynamics towards desirable outcomes
por: Canyakmaz, Ilayda, et al.
Publicado: (2024)

FERNÁNDEZ RAMIL, MARÍA DE LOS ÁNGELES Y RIVERA URRUTIA, EUGENIO. La trastienda del gobierno. El eslabón perdido en la modernización del Estado chileno
por: Enrique Paris Horvitz
Publicado: (2013)

Multiscale nonlinear integration drives accurate encoding of input information
por: Nicoletti, Giorgio, et al.
Publicado: (2024)

Empirical AI Ethics: Reconfiguring Ethics towards a Situated, Plural, and Transformative Approach
por: Helm, Paula, et al.
Publicado: (2025)

Impact of Cathode Microstructure on Sulfur Redox Kinetics in Lithium–Sulfur Batteries
por: Kameron Liao, et al.
Publicado: (2025)

The human‐specific noncoding RNA RP11‐424G14.1 functions at the intersection of sexually dimorphic pathways in inflammation, senescence, and metabolism
por: Kameron Kennicott, et al.
Publicado: (2025)

Perceived threat of climate change in the second half of life
por: Bünning, Mareike, et al.
Publicado: (2025)

Time and change: A meta‐analysis of temporal decisions in longitudinal studies
por: Helen Hailin Zhao, et al.
Publicado: (2024)

Correcting for finite statistics effects in a quantum steering experiment
por: Engineer, Sophie, et al.
Publicado: (2023)

Identifying Spurious Correlations using Counterfactual Alignment
por: Cohen, Joseph Paul, et al.
Publicado: (2023)

Explaining 3D Computed Tomography Classifiers with Counterfactuals
por: Cohen, Joseph Paul, et al.
Publicado: (2025)