Pitfalls in language models for code intelligence: A taxonomy and survey
Modern language models (LMs) have been successfully employed in source code
generation and understanding, leading to a significant increase in research focused on …
generation and understanding, leading to a significant increase in research focused on …
Fully autonomous programming with large language models
Current approaches to program synthesis with Large Language Models (LLMs) exhibit a"
near miss syndrome": they tend to generate programs that semantically resemble the correct …
near miss syndrome": they tend to generate programs that semantically resemble the correct …
Trustworthy and synergistic artificial intelligence for software engineering: Vision and roadmaps
D Lo - 2023 IEEE/ACM International Conference on Software …, 2023 - ieeexplore.ieee.org
For decades, much software engineering research has been dedicated to devising
automated solutions aimed at enhancing developer productivity and elevating software …
automated solutions aimed at enhancing developer productivity and elevating software …
A survey on large language models for software engineering
Software Engineering (SE) is the systematic design, development, and maintenance of
software applications, underpinning the digital infrastructure of our modern mainworld. Very …
software applications, underpinning the digital infrastructure of our modern mainworld. Very …
An Empirical Study of Parameter-Efficient Fine-Tuning Methods for Pre-Trained Code Models
J Liu, C Sha, X Peng - 2023 38th IEEE/ACM International …, 2023 - ieeexplore.ieee.org
Pre-trained code models (eg CodeBERT and CodeT5) have demonstrated their code
intelligence in various software engineering tasks, such as code summarization. And full fine …
intelligence in various software engineering tasks, such as code summarization. And full fine …
CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences
M Weyssow, A Kamanda, H Sahraoui - arXiv preprint arXiv:2403.09032, 2024 - arxiv.org
Evaluating the alignment of large language models (LLMs) with user-defined coding
preferences is a challenging endeavour that requires assessing intricate textual LLMs' …
preferences is a challenging endeavour that requires assessing intricate textual LLMs' …
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
Language models can serve as a valuable tool for software developers to increase
productivity. Large generative models can be used for code generation and code …
productivity. Large generative models can be used for code generation and code …