Zobrazeno 1 - 10
of 14 443
pro vyhledávání: '"Wu, Cheng"'
Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information from large language models (LLMs). This study investigates whether such
Externí odkaz:
http://arxiv.org/abs/2408.02442
In this study, we explore the proactive ability of LLMs to seek user support, using text-to-SQL generation as a case study. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investigate whether LLMs ca
Externí odkaz:
http://arxiv.org/abs/2407.14767
Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capa
Externí odkaz:
http://arxiv.org/abs/2406.08747
In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to option order an
Externí odkaz:
http://arxiv.org/abs/2406.03009
Autor:
Liu, Lu-Chuan, Wu, Cheng, Li, Wei, Chen, Yu-Ao, Wilczek, Frank, Shao, Xiao-Peng, Xu, Feihu, Zhang, Qiang, Pan, Jian-Wei
Long baseline diffraction-limited optical aperture synthesis technology by interferometry plays an important role in scientific study and practical application. In contrast to amplitude (phase) interferometry, intensity interferometry -- which exploi
Externí odkaz:
http://arxiv.org/abs/2404.15685
Autor:
Kang, Eugene Yu-Chuan, Yeung, Ling, Lee, Yi-Lun, Wu, Cheng-Hsiu, Peng, Shu-Yen, Chen, Yueh-Peng, Gao, Quan-Ze, Lin, Chihung, Kuo, Chang-Fu, Lai, Chi-Chun
Publikováno v:
JMIR Medical Informatics, Vol 9, Iss 5, p e28868 (2021)
BackgroundRetinal vascular diseases, including diabetic macular edema (DME), neovascular age-related macular degeneration (nAMD), myopic choroidal neovascularization (mCNV), and branch and central retinal vein occlusion (BRVO/CRVO), are considered vi
Externí odkaz:
https://doaj.org/article/c70e5e4129da4d319edd26bbd0fd7c2b
This paper presents a novel approach to network pruning, targeting block pruning in deep neural networks for edge computing environments. Our method diverges from traditional techniques that utilize proxy metrics, instead employing a direct block rem
Externí odkaz:
http://arxiv.org/abs/2312.16904
Autor:
Li, Lok Yee Joyce, Wang, Shin-Yi, Wu, Cheng-Jung, Tsai, Cheng-Yu, Wu, Te-Fang, Lin, Yaoh-Shiang
Publikováno v:
JMIR mHealth and uHealth, Vol 8, Iss 10, p e17213 (2020)
BackgroundHearing impairment is the most frequent sensory deficit in humans, affecting more than 360 million people worldwide. In fact, hearing impairment is not merely a health problem, but it also has a great impact on the educational performance,
Externí odkaz:
https://doaj.org/article/d1d16c5c220f4298b5ee266b7f18fdf5
In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential inaccuraci
Externí odkaz:
http://arxiv.org/abs/2310.14981
Autor:
Wu, Cheng, Wang, Chaokun, Xu, Jingcao, Liu, Ziyang, Zheng, Kai, Wang, Xiaowei, Song, Yang, Gai, Kun
Graph Neural Networks (GNNs) have demonstrated promising results on exploiting node representations for many downstream tasks through supervised end-to-end training. To deal with the widespread label scarcity issue in real-world applications, Graph C
Externí odkaz:
http://arxiv.org/abs/2308.00535