Zobrazeno 1 - 10
of 126
pro vyhledávání: '"JIANG Dongwei"'
Autor:
Jiang, Dongwei, Wang, Guoxuan, Lu, Yining, Wang, Andrew, Zhang, Jingyu, Liu, Chuyu, Van Durme, Benjamin, Khashabi, Daniel
The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are frequently left implicit (unstated). To address this challenge, we int
Externí odkaz:
http://arxiv.org/abs/2410.01044
Autor:
Sprague, Zayne, Yin, Fangcong, Rodriguez, Juan Diego, Jiang, Dongwei, Wadhwa, Manya, Singhal, Prasann, Zhao, Xinyu, Ye, Xi, Mahowald, Kyle, Durrett, Greg
Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a quantitative me
Externí odkaz:
http://arxiv.org/abs/2409.12183
As LLMs become increasingly prevalent, it is interesting to consider how ``creative'' these models can be. From cognitive science, creativity consists of at least two key characteristics: \emph{convergent} thinking (purposefulness to achieve a given
Externí odkaz:
http://arxiv.org/abs/2407.09007
Autor:
Jiang, Dongwei, Zhang, Jingyu, Weller, Orion, Weir, Nathaniel, Van Durme, Benjamin, Khashabi, Daniel
Can LLMs consistently improve their previous outputs for better results? For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this h
Externí odkaz:
http://arxiv.org/abs/2404.04298
Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning. We use Lean, a theorem proving framework, to address these challenges. By formalizing logical rea
Externí odkaz:
http://arxiv.org/abs/2403.13312
Autor:
Weir, Nathaniel, Sanders, Kate, Weller, Orion, Sharma, Shreya, Jiang, Dongwei, Jiang, Zhengping, Mishra, Bhavana Dalvi, Tafjord, Oyvind, Jansen, Peter, Clark, Peter, Van Durme, Benjamin
Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic. However, progress in this direction has been hampe
Externí odkaz:
http://arxiv.org/abs/2402.14798
Publikováno v:
Hangkong bingqi, Vol 31, Iss 5, Pp 41-49 (2024)
This paper reviews the research on InAs/GaSb superlattice mesa etching technology. The physicochemi-cal mechanism and parameter control of wet and dry etching are analyzed to elucidate the influence of process conditions on mesa morphology, so as to
Externí odkaz:
https://doaj.org/article/ef4dc12446cb4ae7912f134f808185eb
Autor:
Zhang, Ye, Shan, Yifan, Chang, Faran, Liang, Yan, Zhang, Xiangyu, Wang, Guowei, Wu, Donghai, Jiang, Dongwei, Hao, Hongyue, Xu, Yingqiang, Ni, Haiqiao, Lu, Dan, Niu, Zhichuan
Publikováno v:
In Infrared Physics and Technology December 2024 143
Publikováno v:
In Journal of Electroanalytical Chemistry 15 January 2025 977
Autor:
Zeng, Shoujun, Zhang, Wenjun, Jin, Yongzhong, Li, Xu, Chen, Ge, Zhang, Zhengquan, Jiang, Dongwei, Liu, Yonghong
Publikováno v:
In Diamond & Related Materials May 2024 145