Copertina

Calibrated Language Models and How to Find Them with Label Smoothing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Jerry, Lu, Peng, Zeng, Qiuhao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
di: Zeng, Qiuhao
Pubblicazione: (2025)

ZETA: Leveraging Z-order Curves for Efficient Top-k Attention
di: Zeng, Qiuhao, et al.
Pubblicazione: (2025)

Mamba Modulation: On the Length Generalization of Mamba
di: Lu, Peng, et al.
Pubblicazione: (2025)

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)
di: Prinster, Drew, et al.
Pubblicazione: (2024)

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
di: Zhang, Jinhao, et al.
Pubblicazione: (2026)

Fantastic Pretraining Optimizers and Where to Find Them
di: Wen, Kaiyue, et al.
Pubblicazione: (2025)

Low Rank Gradients and Where to Find Them
di: Sonthalia, Rishi, et al.
Pubblicazione: (2025)

Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
di: Datta, Shrestha, et al.
Pubblicazione: (2026)

How Well Can a Long Sequence Model Model Long Sequences? Comparing Architechtural Inductive Biases on Long-Context Abilities
di: Huang, Jerry
Pubblicazione: (2024)

Posterior Label Smoothing for Node Classification
di: Heo, Jaeseung, et al.
Pubblicazione: (2024)

Large Language Models Struggle in Token-Level Clinical Named Entity Recognition
di: Lu, Qiuhao, et al.
Pubblicazione: (2024)

Do Large Language Models Know How Much They Know?
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone
di: Hassanpour, Negar, et al.
Pubblicazione: (2025)

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
di: Zong, Chen-Chen, et al.
Pubblicazione: (2024)

Fantastic Bugs and Where to Find Them in AI Benchmarks
di: Truong, Sang, et al.
Pubblicazione: (2025)

GNN Explanations that do not Explain and How to find Them
di: Azzolin, Steve, et al.
Pubblicazione: (2026)

Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
di: Huang, Jerry, et al.
Pubblicazione: (2026)

Variational Learning Induces Adaptive Label Smoothing
di: Yang, Sin-Han, et al.
Pubblicazione: (2025)

How to Square Tensor Networks and Circuits Without Squaring Them
di: Loconte, Lorenzo, et al.
Pubblicazione: (2025)

Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling
di: Wei, Junhao, et al.
Pubblicazione: (2026)

Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
di: Jing, Zihao, et al.
Pubblicazione: (2026)

Calibrated Preference Learning: The Case of Label Ranking
di: Thies, Santo M. A. R., et al.
Pubblicazione: (2026)

Saliency-Aware Regularized Quantization Calibration for Large Language Models
di: Zhao, Yanlong, et al.
Pubblicazione: (2026)

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
di: Huang, Jerry, et al.
Pubblicazione: (2024)

Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
di: Soltany, Milad, et al.
Pubblicazione: (2024)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
di: Bui, Anh, et al.
Pubblicazione: (2025)

How Smoothing is N-simplicial Attention?
di: Dussolle, Alexandre, et al.
Pubblicazione: (2025)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
di: Huang, Huipeng, et al.
Pubblicazione: (2025)

LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?
di: Tamo, J. Ben, et al.
Pubblicazione: (2026)

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
di: Zhang, Zhenyu, et al.
Pubblicazione: (2025)

Confidence Calibration in Large Language Models
di: Michael, Noam, et al.
Pubblicazione: (2026)

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
di: Xie, Zeke, et al.
Pubblicazione: (2020)

Dynamical Label Augmentation and Calibration for Noisy Electronic Health Records
di: Li, Yuhao, et al.
Pubblicazione: (2025)

Policy Gradient for Robust Markov Decision Processes
di: Wang, Qiuhao, et al.
Pubblicazione: (2024)

Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
di: Jing, Zihao, et al.
Pubblicazione: (2026)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
di: Hao, Sai, et al.
Pubblicazione: (2026)

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
di: Xia, Guoxuan, et al.
Pubblicazione: (2024)

The Reliability Paradox: Exploring How Shortcut Learning Undermines Language Model Calibration
di: Bihani, Geetanjali, et al.
Pubblicazione: (2024)

Aligning Evaluation with Clinical Priorities: Calibration, Label Shift, and Error Costs
di: Flores, Gerardo A., et al.
Pubblicazione: (2025)

Transcendence: Generative Models Can Outperform The Experts That Train Them
di: Zhang, Edwin, et al.
Pubblicazione: (2024)