Code translation is a crucial process in software development and migration projects, enabling interoperability between different programming languages and enhancing software adaptability and thus longevity. Traditional automated translation methods rely heavily on handcrafted transformation rules, which often lack flexibility and scalability. Meanwhile, advanced language models present promising alternatives but are often limited by proprietary, API-based implementations that raise concerns over data security and reliance. In this paper, we present Auto-Train for Code Translation (ACT), an innovative framework that aims to improve code translation capabilities by enabling in-house finetuning of open-source Large Language Models (LLMs). ACT's automated pipeline significantly boosts the performance of these models, narrowing the gap between open-source accessibility and the high performance of closed-source solutions. Central to ACT is its synthetic data generation module, which builds extensive, high-quality datasets from initial code samples, incorporating unit tests to ensure functional accuracy and diversity. ACT's evaluation framework incorporates execution-level checks, offering a comprehensive assessment of translation quality. A key feature in ACT is its controller module, which manages the entire pipeline by dynamically adjusting hyperparameters, orchestrating iterative data generation, and finetuning based on real-time evaluations. This enables ACT to intelligently optimize when to continue training, generate additional targeted training data, or stop the process. Our results demonstrate that ACT consistently enhances the effectiveness of open-source models, offering businesses and developers a secure and reliable alternative. Additionally, applying our data generation pipeline to industry-scale migration projects has led to a notable increase in developer acceleration.

Recent advancements in large language models, including GPT-4 and its variants, and Generative AI-assisted coding tools like GitHub Copilot, ChatGPT, and Tabnine, have significantly transformed software development. This paper analyzes how these innovations impact productivity and software test development metrics. These tools enable developers to generate complete software programs with minimal human intervention before deployment. However, thorough review and testing by developers are still crucial. Utilizing the Test Pyramid concept, which categorizes tests into unit, integration, and end-to-end tests, we evaluate three popular AI coding assistants by generating and comparing unit tests for opensource modules. Our findings show that AI-generated tests are of equivalent quality to original tests, highlighting differences in usage and results among the tools. This research enhances the understanding and capabilities of AI-assistant tools in automated testing.

Retrieval Augmented Generation (RAG) has shown notable advancements in software engineering tasks. Despite its potential, RAG's application in unit test generation remains under-explored. To bridge this gap, we take the initiative to investigate the efficacy of RAG-based LLMs in test generation. As RAGs can leverage various knowledge sources to enhance their performance, we also explore the impact of different sources of RAGs' knowledge bases on unit test generation to provide insights into their practical benefits and limitations. Specifically, we examine RAG built upon three types of domain knowledge: 1) API documentation, 2) GitHub issues, and 3) StackOverflow Q&As. Each source offers essential knowledge for creating tests from different perspectives, i.e., API documentations provide official API usage guidelines, GitHub issues offer resolutions of issues related to the APIs from the library developers, and StackOverflow Q&As present community-driven solutions and best practices. For our experiment, we focus on five widely used and typical Python-based machine learning (ML) projects, i.e., TensorFlow, PyTorch, Scikit-learn, Google JAX, and XGBoost to build, train, and deploy complex neural networks efficiently. We conducted experiments using the top 10% most widely used APIs across these projects, involving a total of 188 APIs. We investigate the effectiveness of four state-of-the-art LLMs (open and closed-sourced), i.e., GPT-3.5-Turbo, GPT-4o, Mistral MoE 8x22B, and Llamma 3.1 405B. Additionally, we compare three prompting strategies in generating unit test cases for the experimental APIs, i.e., zero-shot, a Basic RAG, and an API-level RAG on the three external sources. Finally, we compare the cost of different sources of knowledge used for the RAG.

With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt ChatGPT to generate a set of instructions and answers, for the student model to learn. However, such standard distillation approach neglects the merits and conditions of the student model. Inspired by modern teaching principles, we design a personalised distillation process, in which the student attempts to solve a task first, then the teacher provides an adaptive refinement for the student to improve. Instead of feeding the student with teacher's prior, personalised distillation enables personalised learning for the student model, as it only learns on examples it makes mistakes upon and learns to improve its own solution. On code generation, personalised distillation consistently outperforms standard distillation with only one third of the data. With only 2.5-3K personalised examples that incur a data-collection cost of 4-6$, we boost CodeGen-mono-16B by 7% to achieve 36.4% pass@1 and StarCoder by 12.2% to achieve 45.8% pass@1 on HumanEval.