Recent researchers have explored code generation Nowadays, LLMs have been successfully used to task by using LLMs; however, most studies (Li support developers' daily development, such as et al., 2023b, 2022a; Ahmad et al., 2021; Hu et al., code generation, test generation, etc. However, 2021) focus on generating "correct" code. There existing Code LLMs are usually general models is limited research investigating how to generate trained with large programming corpus (Zheng "personalized" code, especially for multi-user personalization, et al., 2023; Chen et al., 2022), therefore the generated with no research conducted yet. Automatically code is difficult to adapt to personalized and/or generating code according to developers' customized requests. Consider the following practical preferences or projects' consistency is a challenging scenarios: Alice is a software developer. To task: (i) Considering different programmers improve programmers' daily efficiency, her company have their own coding styles, it is too expensive provided the base LLMs that can be used for to fine-tune an LLM for each user (Guo et al., code generation.

Like text, programs have styles, and certain programming styles are more desirable than others for program readability, maintainability, and performance. Code style transfer, however, is difficult to automate except for trivial style guidelines such as limits on line length. Inspired by the success of using language models for text style transfer, we investigate if code language models can perform code style transfer. Code style transfer, unlike text transfer, has rigorous requirements: the system needs to identify lines of code to change, change them correctly, and leave the rest of the program untouched. We designed CSB (Code Style Benchmark), a benchmark suite of code style transfer tasks across five categories including converting for-loops to list comprehensions, eliminating duplication in code, adding decorators to methods, etc. We then used these tests to see if large pre-trained code language models or fine-tuned models perform style transfer correctly, based on rigorous metrics to test that the transfer did occur, and the code still passes functional tests. Surprisingly, language models failed to perform all of the tasks, suggesting that they perform poorly on tasks that require code understanding. We will make available the large-scale corpora to help the community build better code models.

Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose RLCF, that further trains a pre-trained LLM via reinforcement learning, using feedback from a grounding function that scores the quality of the code. The grounding function uses (i) compiler-derived feedback on whether the code it generates passes a set of correctness checks; and (ii) feedback from a different LLM that compares the generated code to a reference code. RLCF is model- and language-agnostic. We empirically evaluate it on the MBJP and MathQA tasks for Java. Our experiments show that RLCF raises the odds that an LLM-generated program compiles, is executable, and produces the right output on tests, often allowing LLMs to match the performance of 2x-8x larger LLMs.