Zobrazeno 1 - 10
of 45 813
pro vyhledávání: '"Uncertainty Estimation"'
Large Language Models (LLMs) are increasingly employed in real-world applications, driving the need to evaluate the trustworthiness of their generated text. To this end, reliable uncertainty estimation is essential. Since current LLMs generate text a
Externí odkaz:
http://arxiv.org/abs/2412.15176
Autor:
Cádiz-Leyton, Martina, Cabrera-Vives, Guillermo, Protopapas, Pavlos, Moreno-Cartagena, Daniel, Donoso-Oliva, Cristobal, Becker, Ignacio
Classifying variable stars is key for understanding stellar evolution and galactic dynamics. With the demands of large astronomical surveys, machine learning models, especially attention-based neural networks, have become the state-of-the-art. While
Externí odkaz:
http://arxiv.org/abs/2412.10528
Large Language Models (LLMs) display formidable capabilities in generative tasks but also pose potential risks due to their tendency to generate hallucinatory responses. Uncertainty Quantification (UQ), the evaluation of model output reliability, is
Externí odkaz:
http://arxiv.org/abs/2412.07255
Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forwar
Externí odkaz:
http://arxiv.org/abs/2412.07169
Autor:
Sun, Tao, Bohté, Sander
Uncertainty estimation is a standard tool to quantify the reliability of modern deep learning models, and crucial for many real-world applications. However, efficient uncertainty estimation methods for spiking neural networks, particularly for regres
Externí odkaz:
http://arxiv.org/abs/2412.00278
As large language models (LLMs) continue to evolve, understanding and quantifying the uncertainty in their predictions is critical for enhancing application credibility. However, the existing literature relevant to LLM uncertainty estimation often re
Externí odkaz:
http://arxiv.org/abs/2410.15326
Effective human-machine collaboration requires machine learning models to externalize uncertainty, so users can reflect and intervene when necessary. For language models, these representations of uncertainty may be impacted by sycophancy bias: procli
Externí odkaz:
http://arxiv.org/abs/2410.14746
Autor:
Radchenko, Gleb, Fill, Victoria Andrea
Recent advancements in edge computing have significantly enhanced the AI capabilities of Internet of Things (IoT) devices. However, these advancements introduce new challenges in knowledge exchange and resource management, particularly addressing the
Externí odkaz:
http://arxiv.org/abs/2410.08651
Autor:
Messuti, Giovanni, Amoroso, ortensia, Napolitano, Ferdinando, Falanga, Mariarosaria, Capuano, Paolo, Scarpetta, Silvia
Deep learning models have demonstrated remarkable success in various fields, including seismology. However, one major challenge in deep learning is the presence of mislabeled examples. Additionally, accurately estimating model uncertainty is another
Externí odkaz:
http://arxiv.org/abs/2410.06120
Deep Learning-based image super-resolution (SR) has been gaining traction with the aid of Generative Adversarial Networks. Models like SRGAN and ESRGAN are constantly ranked between the best image SR tools. However, they lack principled ways for esti
Externí odkaz:
http://arxiv.org/abs/2412.15439