Imagen de Portada

When to Accept Automated Predictions and When to Defer to Human Judgment?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sikar, Daniel, Garcez, Artur, Weyde, Tillman, Bloomfield, Robin, Peeroo, Kaleem
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
por: Sikar, Daniel, et al.
Publicado: (2025)

The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others
por: Sikar, Daniel, et al.
Publicado: (2024)

Evaluation of autonomous systems under data distribution shifts
por: Sikar, Daniel, et al.
Publicado: (2024)

Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification
por: Velarde, Gissel, et al.
Publicado: (2025)

An approach to melodic segmentation and classification based on filtering with the Haar-wavelet
por: Velarde, Gissel, et al.
Publicado: (2025)

Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing
por: Mitton, Joshua, et al.
Publicado: (2025)

Derivative-based regularization for regression
por: Lopedoto, Enrico, et al.
Publicado: (2024)

When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
por: Liu, Shuqi, et al.
Publicado: (2026)

Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
por: Montreuil, Yannis, et al.
Publicado: (2025)

Evaluating LLMs for Combinatorial Optimization: One-Phase and Two-Phase Heuristics for 2D Bin-Packing
por: Huq, Syed Mahbubul, et al.
Publicado: (2025)

Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
por: Pugnana, Andrea, et al.
Publicado: (2025)

When Layers Play the Lottery, all Tickets Win at Initialization
por: Jordao, Artur, et al.
Publicado: (2023)

When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
por: Feuer, Benjamin, et al.
Publicado: (2025)

Accept-Reject Lasso
por: Liu, Yanxin, et al.
Publicado: (2025)

Honesty in Causal Forests: When It Helps and When It Hurts
por: Hou, Yanfang, et al.
Publicado: (2025)

FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series
por: Su, Qiqi, et al.
Publicado: (2023)

Relative Overfitting and Accept-Reject Framework
por: Liu, Yanxin, et al.
Publicado: (2025)

SkipPredict: When to Invest in Predictions for Scheduling
por: Shahout, Rana, et al.
Publicado: (2024)

Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
por: Amin, Hasan, et al.
Publicado: (2026)

Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features
por: Xu, Yi, et al.
Publicado: (2026)

When Machine Learning Gets Personal: Evaluating Prediction and Explanation
por: Cornelis, Louisa, et al.
Publicado: (2025)

Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
por: Wu, Zixuan, et al.
Publicado: (2025)

Learning to Partially Defer for Sequences
por: Rayan, Sahana, et al.
Publicado: (2025)

Learning-to-Defer with Expert-Conditional Advice
por: Montreuil, Yannis, et al.
Publicado: (2026)

Online Learning-to-Defer with Varying Experts
por: Duy, Dang Hoang, et al.
Publicado: (2026)

When Should Humans Step In? Optimal Human Dispatching in AI-Assisted Decisions
por: Tan, Lezhi, et al.
Publicado: (2026)

CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
por: Singh, Ankush Pratap, et al.
Publicado: (2025)

When Models Don't Collapse: On the Consistency of Iterative MLE
por: Barzilai, Daniel, et al.
Publicado: (2025)

LoRA and Privacy: When Random Projections Help (and When They Don't)
por: Hu, Yaxi, et al.
Publicado: (2026)

When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
por: Zhang, Zhihan, et al.
Publicado: (2025)

Online Conformal Selection with Accept-to-Reject Changes
por: Liu, Kangdao, et al.
Publicado: (2025)

Learning When to Adapt
por: Zindari, Ali, et al.
Publicado: (2026)

When Is Compositional Reasoning Learnable from Verifiable Rewards?
por: Barzilai, Daniel, et al.
Publicado: (2026)

When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
por: Heo, Heeyun, et al.
Publicado: (2026)

When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
por: Steiner, Dylan, et al.
Publicado: (2026)

Robust Validation: Confident Predictions Even When Distributions Shift
por: Cauchois, Maxime, et al.
Publicado: (2020)

Investigating task-specific prompts and sparse autoencoders for activation monitoring
por: Tillman, Henk, et al.
Publicado: (2025)

Adversarial Robustness in One-Stage Learning-to-Defer
por: Montreuil, Yannis, et al.
Publicado: (2025)

Principled Approaches for Learning to Defer with Multiple Experts
por: Mao, Anqi, et al.
Publicado: (2023)

When and How to Fool Explainable Models (and Humans) with Adversarial Examples
por: Vadillo, Jon, et al.
Publicado: (2021)