作者：
LEVY, JETHE AUTHOR:His education includes a Bachelor of Science Degree from City College of New York
an M.A. in Mathematics and Mathematics Teaching from New York University and graduate work at Harvard MIT and George Washington University. During World War II he was in charge of radar and electronics maintenance training in the Pacific Fleet Training Center at Pearl Harbor. For five years following the war he worked in the Bureau of Naval Ordnance in Fire Control Engineering. He is now President of Washington Engineering Services Company Inc. which he formed in 1951 and which develops and implements various management and training systems for commercial and Government agencies. Mr. Levy is also President of WESCO Information Utility Inc. a data processing service subsidiary of Washington Engineering Services Company Inc.
The two-volume set LNAI 6634 and 6635 constitutes the refereed proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and data Mining, PAKDD 2011, held in Shenzhen, China in May 2011. The total of 32 r...
详细信息
ISBN:
(数字)9783642208416
ISBN:
(纸本)9783642208409
The two-volume set LNAI 6634 and 6635 constitutes the refereed proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and data Mining, PAKDD 2011, held in Shenzhen, China in May 2011. The total of 32 revised full papers and 58 revised short papers were carefully reviewed and selected from 331 submissions. The papers present new ideas, original research results, and practical development experiences from all KDD-related areas including data mining, machine learning, artificial intelligence and pattern recognition, data warehousing and databases, statistics, knowledge engineering, behavior sciences, visualization, and emerging areas such as social network analysis.
Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fi...
详细信息
Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality *** apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.
The two-volume set LNAI 6634 and 6635 constitutes the refereed proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and data Mining, PAKDD 2011, held in Shenzhen, China in May 2011. The total of 32 r...
详细信息
ISBN:
(数字)9783642208478
ISBN:
(纸本)9783642208461
The two-volume set LNAI 6634 and 6635 constitutes the refereed proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and data Mining, PAKDD 2011, held in Shenzhen, China in May 2011. The total of 32 revised full papers and 58 revised short papers were carefully reviewed and selected from 331 submissions. The papers present new ideas, original research results, and practical development experiences from all KDD-related areas including data mining, machine learning, artificial intelligence and pattern recognition, data warehousing and databases, statistics, knowledge engineering, behavior sciences, visualization, and emerging areas such as social network analysis.
暂无评论