Zobrazeno 1 - 10
of 3 005
pro vyhledávání: '"Cheng Kuang"'
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
This study explores the proactive ability of LLMs to seek user support. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investigate whether LLMs can determine when to request help under varying infor
Externí odkaz:
http://arxiv.org/abs/2407.14767
Autor:
Tseng, Liang-Hsuan, Chen, Zih-Ching, Chang, Wei-Shun, Lee, Cheng-Kuang, Huang, Tsung-Ren, Lee, Hung-yi
Recent advances in automatic speech recognition (ASR) often rely on large speech foundation models for generating high-quality transcriptions. However, these models can be impractical due to limited computing resources. The situation is even more sev
Externí odkaz:
http://arxiv.org/abs/2407.10603
Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge when speaker
Externí odkaz:
http://arxiv.org/abs/2407.01911
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
Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy improvement. In the p
Externí odkaz:
http://arxiv.org/abs/2405.13629
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:
Chun-Li Wang, Shian-Shiang Wang, Chuan-Shu Chen, Sheng-Chun Hung, Cheng-Che Chen, Cheng-Kuang Yang, Jian-Ri Li, Kun-Yuan Chiu, Chia-Yen Lin
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-7 (2024)
Abstract Bone health screening is crucial before and during androgen deprivation therapy (ADT) for prostate cancer, yet changes in bone mineral density during ADT are often overlooked. To improve surveillance rates, we developed an auto-recruit path
Externí odkaz:
https://doaj.org/article/0130a8e7460e4611bac07d3d92b33f53
Autor:
Chia-Yen Lin, Chun-Li Wang, Cheng-Kuang Yang, Jian-Ri Li, Chuan-Shu Chen, Kun-Yuan Chiu, Ching-Heng Lin, Shian-Shiang Wang
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-10 (2024)
Abstract Prostate cancer (PC) treatment, particularly androgen deprivation therapy (ADT), remains pivotal, albeit linked to increased fracture risk due to osteoporosis. The advent of novel hormonal agents (NHAs) has spurred inquiries into their influ
Externí odkaz:
https://doaj.org/article/151f502bed2a49348114f19e43d30bad