Utilizing state-of-the-art Large Language Models (LLMs), automatic code generation models play a pivotal role in enhancing the productivity of software development procedures. As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models, yet is under-explored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive evaluation of the bias in code generated by five state-of-the-art LLMs. Our findings reveal that 20.29% to 44.93% code functions generated by the models under study are biased when handling bias sensitive tasks (i.e., tasks that involve sensitive attributes such as age and gender). This indicates that the existing LLMs can be unfair in code generation, posing risks of unintended and harmful software behaviors. To mitigate bias for code generation models, we evaluate five bias mitigation prompt strategies, i.e., utilizing bias testing results to refine the code (zero-shot), one-, few-shot, and two Chain-of-Thought (CoT) prompts. Our evaluation results illustrate that these strategies are all effective in mitigating bias. Overall, one-shot and few-shot learning are the two most effective. For GPT-4, 80% to 90% code bias can be removed with one-shot learning.

Vulnerability identification is crucial to protect software systems from attacks for cyber-security. However, huge projects have more than millions of lines of code, and the complex dependencies make it hard to carry out traditional static and dynamic methods. Furthermore, the semantic structure of various types of vulnerabilities differs greatly and may occur simultaneously, making general rule-based methods difficult to extend. In this paper, we propose \textit{Vignat}, a novel attention-based framework for identifying vulnerabilities by learning graph-level semantic representations of code. We represent codes with code property graphs (CPGs) in fine grain and use graph attention networks (GATs) for vulnerability detection. The results show that Vignat is able to achieve $57.38\%$ accuracy on reliable datasets derived from popular C libraries. Furthermore, the interpretability of our GATs provides valuable insights into vulnerability patterns.

In natural language processing, transformer-based large language models (LLMs) like GPT-x models developed by OpenAI have revolutionized the landscape. Despite their impressive capabilities, these models often encounter challenges when handling tasks that differ from their training data, resulting in compromised performance. To address this, few-shot learning has emerged as a valuable technique, allowing LLMs to adapt with minimal task-specific data. One innovative strategy, known as Chain-of-Thought Prompting (CoT), has been introduced to guide LLMs in revealing cognitive processes during multi-step reasoning. In this paper, we propose Code Chain-of-Thought~(CodeCoT), which consists of two components: the Vanilla CodeCoT and the Self-exam CodeCoT. The latter incorporates self-examination, empowering the model to iteratively generate code, formulate test cases, and refine its outputs. Specifically, the process entails the generation of test examples by the model corresponding to the code it is tasked to implement. If it fails on the test examples, then it regenerates the code based on the erroneous code and associated error types. Through comprehensive experiments, we observed that both techniques significantly enhance code generation accuracy across various LLM variants. Our evaluation results reveal that CodeCoT improves the code generation effectiveness, including an unprecedented pass@1 accuracy of 79.27\% using the Self-exam CodeCoT approach on the gpt-3.5-turbo-0613 model in the HumanEval dataset.

In this blog, you'll learn what Keras callback is, when it is called, what it can do and how it can be used. When you train a model, you try to achieve the best accuracy on your training data but whereas it's possible to reach really good accuracy on the training set, what we really want is to train models that generalize well to the testing(unseen) data. In trying to achieve this we often come across the concept of overfitting. Since training data is what the network learns from, we take the measure of accuracy on training data as one of our metrics. But the test data may be very different from the training set.