Copertina

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Beier, Wang, Shuoyuan, Li, Sharon, Wei, Hongxin
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

Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs
di: Luo, Beier, et al.
Pubblicazione: (2026)

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
di: Zhang, Jiaxing, et al.
Pubblicazione: (2025)

Confidence Calibration under Ambiguous Ground Truth
di: Tao, Linwei, et al.
Pubblicazione: (2026)

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
di: Kim, JaeYoon, et al.
Pubblicazione: (2024)

Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
di: Wang, Shuoyuan, et al.
Pubblicazione: (2023)

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model
di: Jin, Jiarui, et al.
Pubblicazione: (2025)

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
di: Tian, Shiyu, et al.
Pubblicazione: (2023)

Your Transformer is Secretly Linear
di: Razzhigaev, Anton, et al.
Pubblicazione: (2024)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
di: Naganuma, Hiroki, et al.
Pubblicazione: (2023)

Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
di: Wang, Shuoyuan, et al.
Pubblicazione: (2024)

Confidence Calibration of Classifiers with Many Classes
di: LeCoz, Adrien, et al.
Pubblicazione: (2024)

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

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
di: Zhang, Xuan, et al.
Pubblicazione: (2024)

Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
di: Yang, Muli, et al.
Pubblicazione: (2026)

Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning
di: Ying, Wangyang, et al.
Pubblicazione: (2024)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
di: Chen, Hao, et al.
Pubblicazione: (2023)

Demystifying Manifold Constraints in LLM Pre-training
di: An, Kang, et al.
Pubblicazione: (2026)

Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
di: Miyashita, Hisashi
Pubblicazione: (2026)

How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2025)

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

OSF: On Pre-training and Scaling of Sleep Foundation Models
di: Shuai, Zitao, et al.
Pubblicazione: (2026)

Graph Generative Pre-trained Transformer
di: Chen, Xiaohui, et al.
Pubblicazione: (2025)

Your Dense Retriever is Secretly an Expeditious Reasoner
di: Zhang, Yichi, et al.
Pubblicazione: (2025)

Your Learned Constraint is Secretly a Backward Reachable Tube
di: Qadri, Mohamad, et al.
Pubblicazione: (2025)

Open-Vocabulary Calibration for Fine-tuned CLIP
di: Wang, Shuoyuan, et al.
Pubblicazione: (2024)

Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
di: Liu, Ning, et al.
Pubblicazione: (2026)

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
di: Pappalardo, Octavio
Pubblicazione: (2026)

Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection
di: Xu, Hongzuo, et al.
Pubblicazione: (2022)

Secret mixtures of experts inside your LLM
di: Boix-Adsera, Enric
Pubblicazione: (2025)

Graph-based Confidence Calibration for Large Language Models
di: Li, Yukun, et al.
Pubblicazione: (2024)

Confidence-gated training for efficient early-exit neural networks
di: Mokssit, Saad, et al.
Pubblicazione: (2025)

Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
di: Chitnis, Soham Rohit, et al.
Pubblicazione: (2023)

Your Absorbing Discrete Diffusion Secretly Models the Bayesian Posterior
di: Doyle, Cooper
Pubblicazione: (2025)

When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
di: Casey, Emma, et al.
Pubblicazione: (2026)

Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
di: Niu, Peisong, et al.
Pubblicazione: (2025)

Pre-training with Synthetic Data Helps Offline Reinforcement Learning
di: Wang, Zecheng, et al.
Pubblicazione: (2023)

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
di: Liu, Xin, et al.
Pubblicazione: (2023)

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks
di: Luo, Jiayi, et al.
Pubblicazione: (2025)

TripCast: Pre-training of Masked 2D Transformers for Trip Time Series Forecasting
di: Liao, Yuhua, et al.
Pubblicazione: (2024)

Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model
di: Kallus, Nathan
Pubblicazione: (2025)