Zobrazeno 1 - 10
of 154
pro vyhledávání: '"Ray, Baishakhi"'
In this study, we address the issue of API hallucinations in various software engineering contexts. We introduce CloudAPIBench, a new benchmark designed to measure API hallucination occurrences. CloudAPIBench also provides annotations for frequencies
Externí odkaz:
http://arxiv.org/abs/2407.09726
Prior research has enhanced the ability of Large Language Models (LLMs) to solve logic puzzles using techniques such as chain-of-thought prompting or introducing a symbolic representation. These frameworks are still usually insufficient to solve comp
Externí odkaz:
http://arxiv.org/abs/2407.03956
Autor:
Mathai, Alex, Huang, Chenxi, Maniatis, Petros, Nogikh, Aleksandr, Ivancic, Franjo, Yang, Junfeng, Ray, Baishakhi
Large Language Models (LLMs) are consistently improving at increasingly realistic software engineering (SE) tasks. In real-world software stacks, significant SE effort is spent developing foundational system software like the Linux kernel. Unlike app
Externí odkaz:
http://arxiv.org/abs/2407.02680
Autor:
Wang, Junlin, Jain, Siddhartha, Zhang, Dejiao, Ray, Baishakhi, Kumar, Varun, Athiwaratkun, Ben
A diverse array of reasoning strategies has been proposed to elicit the capabilities of large language models. However, in this paper, we point out that traditional evaluations which focus solely on performance metrics miss a key factor: the increase
Externí odkaz:
http://arxiv.org/abs/2406.06461
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
Autor:
Jiang, Nan, Li, Xiaopeng, Wang, Shiqi, Zhou, Qiang, Hossain, Soneya Binta, Ray, Baishakhi, Kumar, Varun, Ma, Xiaofei, Deoras, Anoop
In the domain of code generation, self-debugging is crucial. It allows LLMs to refine their generated code based on execution feedback. This is particularly important because generating correct solutions in one attempt proves challenging for complex
Externí odkaz:
http://arxiv.org/abs/2405.18649
Large language models (LLMs) are increasingly being used for the task of automated code translation, which has important real-world applications. However, most existing approaches use only the source code of a program as an input to an LLM, and do no
Externí odkaz:
http://arxiv.org/abs/2405.18574
Autor:
Lyu, Michael R., Ray, Baishakhi, Roychoudhury, Abhik, Tan, Shin Hwei, Thongtanunam, Patanamon
Automatic programming has seen increasing popularity due to the emergence of tools like GitHub Copilot which rely on Large Language Models (LLMs). At the same time, automatically generated code faces challenges during deployment due to concerns aroun
Externí odkaz:
http://arxiv.org/abs/2405.02213
Autor:
Zhang, Yuhao, Wang, Shiqi, Qian, Haifeng, Wang, Zijian, Shang, Mingyue, Liu, Linbo, Gouda, Sanjay Krishna, Ray, Baishakhi, Ramanathan, Murali Krishna, Ma, Xiaofei, Deoras, Anoop
Code generation models are not robust to small perturbations, which often lead to inconsistent and incorrect generations and significantly degrade the performance of these models. Improving the robustness of code generation models is crucial to bette
Externí odkaz:
http://arxiv.org/abs/2405.01567
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