Výsledky vyhledávání - "Min, Marcus J."

Report

SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

Autor: Ding, Yangruibo, Peng, Jinjun, Min, Marcus J., Kaiser, Gail, Yang, Junfeng, Ray, Baishakhi

Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text data and the

Externí odkaz: http://arxiv.org/abs/2406.01006

Zobrazit plný text záznamu

Report

CYCLE: Learning to Self-Refine the Code Generation

Autor: Ding, Yangruibo, Min, Marcus J., Kaiser, Gail, Ray, Baishakhi

Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers. However, their self-refinement capability is typically overlooked by the existing evaluations of code

Externí odkaz: http://arxiv.org/abs/2403.18746

Zobrazit plný text záznamu

Report

Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

Autor: Min, Marcus J., Ding, Yangruibo, Buratti, Luca, Pujar, Saurabh, Kaiser, Gail, Jana, Suman, Ray, Baishakhi

Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their self-consiste

Externí odkaz: http://arxiv.org/abs/2310.14053

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání