Image de couverture de livre

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Changlong, Grama, Ananth, Szpankowski, Wojciech
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Robust Online Classification: From Estimation to Denoising
par: Wu, Changlong, et autres
Publié: (2023)

Generalized Learning of Coefficients in Spectral Graph Convolutional Networks
par: Coşkun, Mustafa, et autres
Publié: (2024)

Oracle-Efficient Hybrid Online Learning with Unknown Distribution
par: Wu, Changlong, et autres
Publié: (2024)

Inference-Time Code Selection via Symbolic Equivalence Partitioning
par: Cho, David, et autres
Publié: (2026)

Celo2: Towards Learned Optimization Free Lunch
par: Moudgil, Abhinav, et autres
Publié: (2026)

Online Distribution Learning with Local Private Constraints
par: Sima, Jin, et autres
Publié: (2024)

No-Free-Lunch Theories for Tensor-Network Machine Learning Models
par: Wu, Jing-Chuan, et autres
Publié: (2024)

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
par: Zhang, Yanzhi, et autres
Publié: (2025)

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
par: Wagner, Moritz, et autres
Publié: (2025)

Fundamental Limits of Membership Inference Attacks on Machine Learning Models
par: Aubinais, Eric, et autres
Publié: (2023)

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs
par: Li, Qingyuan, et autres
Publié: (2024)

Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement
par: Wei, Yuhan, et autres
Publié: (2026)

Separable Power of Classical and Quantum Learning Protocols Through the Lens of No-Free-Lunch Theorem
par: Wang, Xinbiao, et autres
Publié: (2024)

A No Free Lunch Theorem for Human-AI Collaboration
par: Peng, Kenny, et autres
Publié: (2024)

Activation Sensitivity as a Unifying Principle for Post-Training Quantization
par: Xu, Bruce Changlong
Publié: (2026)

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
par: Wang, Zehan, et autres
Publié: (2024)

Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss
par: Getu, Tilahun M., et autres
Publié: (2023)

LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
par: Zhang, Weizhi, et autres
Publié: (2025)

Hallucination is Inevitable: An Innate Limitation of Large Language Models
par: Xu, Ziwei, et autres
Publié: (2024)

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
par: Li, Haoran, et autres
Publié: (2026)

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
par: Ding, Zeyang, et autres
Publié: (2026)

Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework
par: Chen, Shengchao, et autres
Publié: (2024)

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
par: Chen, Fan, et autres
Publié: (2025)

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
par: Liu, Tao, et autres
Publié: (2025)

You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models
par: Roy, Shuvendu, et autres
Publié: (2025)

Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
par: Praski, Mateusz, et autres
Publié: (2025)

Towards General-Purpose Model-Free Reinforcement Learning
par: Fujimoto, Scott, et autres
Publié: (2025)

Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives
par: Afshar, Aida, et autres
Publié: (2024)

Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning
par: Wu, Jiayun, et autres
Publié: (2025)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
par: Zhang, Bingjie, et autres
Publié: (2025)

New Bounds on Quantum Sample Complexity of Measurement Classes
par: Heidari, Mohsen, et autres
Publié: (2024)

Generalization Limits of Reinforcement Learning Alignment
par: Shida, Haruhi, et autres
Publié: (2026)

On the Fundamental Impossibility of Hallucination Control in Large Language Models
par: Karpowicz, Michał P.
Publié: (2025)

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
par: Lu, Rui, et autres
Publié: (2025)

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
par: Chen, Mouxiang, et autres
Publié: (2024)

Model Science: getting serious about verification, explanation and control of AI systems
par: Biecek, Przemyslaw, et autres
Publié: (2025)

ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models
par: Defazio, Aaron
Publié: (2026)

BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
par: Huang, Baichuan, et autres
Publié: (2025)

On the Limitations and Prospects of Machine Unlearning for Generative AI
par: Zhou, Shiji, et autres
Publié: (2024)

Imagination-Limited Q-Learning for Offline Reinforcement Learning
par: Liu, Wenhui, et autres
Publié: (2025)