Výsledky vyhledávání - "Jiang Yanfei"

Report

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning

Autor: Liu, Yilun, Tao, Shimin, Zhao, Xiaofeng, Zhu, Ming, Ma, Wenbing, Zhu, Junhao, Su, Chang, Hou, Yutai, Zhang, Miao, Zhang, Min, Ma, Hongxia, Zhang, Li, Yang, Hao, Jiang, Yanfei

Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of high-quality ins

Externí odkaz: http://arxiv.org/abs/2311.13246

Zobrazit plný text záznamu

Report

Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies

Autor: Liu, Yilun, Tao, Shimin, Meng, Weibin, Wang, Jingyu, Ma, Wenbing, Zhao, Yanqing, Chen, Yuhang, Yang, Hao, Jiang, Yanfei, Chen, Xun

Automated log analysis is crucial in modern software-intensive systems for facilitating program comprehension throughout software maintenance and engineering life cycles. Existing methods perform tasks such as log parsing and log anomaly detection by

Externí odkaz: http://arxiv.org/abs/2308.07610

Zobrazit plný text záznamu

Report

Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment

Autor: Yang, Hao, Zhang, Min, Tao, Shimin, Wang, Minghan, Wei, Daimeng, Jiang, Yanfei

Cross-lingual Machine Translation (MT) quality estimation plays a crucial role in evaluating translation performance. GEMBA, the first MT quality assessment metric based on Large Language Models (LLMs), employs one-step prompting to achieve state-of-

Externí odkaz: http://arxiv.org/abs/2306.07486

Zobrazit plný text záznamu

Report

Evaluating GPT's Programming Capability through CodeWars' Katas

Autor: Zhang, Zizhuo, Wen, Lian, Zhang, Shaoyang, Chen, David, Jiang, Yanfei

In the burgeoning field of artificial intelligence (AI), understanding the capabilities and limitations of programming-oriented models is crucial. This paper presents a novel evaluation of the programming proficiency of Generative Pretrained Transfor

Externí odkaz: http://arxiv.org/abs/2306.01784

Zobrazit plný text záznamu