We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both "bimodal" and "unimodal" data. Here, bimodal data is the combination of text and corresponding code snippets, whereas unimodal data is merely code snippets. We first evaluate CoTexT with multi-task learning: we perform Code Summarization on 6 different programming languages and Code Refinement on both small and medium size featured in the CodeXGLUE dataset. We further conduct extensive experiments to investigate CoTexT on other tasks within the CodeXGlue dataset, including Code Generation and Defect Detection. We consistently achieve SOTA results in these tasks, demonstrating the versatility of our models.
Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The target-to-source model generates noisy sources, while the source-to-target model is trained to reconstruct the targets and vice versa. Recent developments of multilingual pre-trained sequence-to-sequence models for programming languages have been very effective for a broad spectrum of downstream software engineering tasks. Hence, training them to build programming language translation systems via back-translation is compelling. However, these models cannot be further trained via back-translation since they learn to output sequences in the same language as the inputs during pre-training. As an alternative, we propose performing back-translation via code summarization and generation. In code summarization, a model learns to generate natural language (NL) summaries given code snippets. In code generation, the model learns to do the opposite. Therefore, target-to-source generation in back-translation can be viewed as a target-to-NL-to-source generation. We show that our proposed approach performs competitively with state-of-the-art methods. We have made the code publicly available.
Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we propose a simple and effective \textbf{u}ncertainty-aware \textbf{s}elective \textbf{c}ontrastive \textbf{d}ecoding ($\mathbb{USCD}$) mechanism to improve the quality of one-pass code generation in LLMs and reduce the impact of output noise. To be specific, we first elaborately designed a negative prompt (namely lame prompt) to output noise by removing input-output examples from the standard few-shot prompt. Our preliminary study shows that the Jensen-Shannon divergence (JS divergence) between token distribution uncertainty and the output noise is relatively low (approximately $0.25$), indicating their high relevance. Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt. Notably, our proposed plug-and-play mechanism is an inference-only method, enjoying appealing flexibility. Extensive experiments on widely used benchmarks, e.g., HumanEval, MBPP, and MultiPL-E, upon several LLMs (i.e., Inocder-6b, CodeLlama-7b, WizardCoder-15b, StarCoder, and Llama2-7b), demonstrate that our proposed USCD significantly improves one-pass code generation, with an average \textit{pass@$1$} scores increase of 16.59\%. We will release code and data on GitHub.
Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains underexplored in the code domain. In this paper, we introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement, with different input and output programming languages. Next, on our CodeTask-CL benchmark, we compare popular CL techniques from NLP and Vision domains. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism caused by stark distribution shifts in coding tasks. We address this issue with our proposed method, Prompt Pooling with Teacher Forcing (PP-TF), that stabilizes training by enforcing constraints on the prompt selection mechanism and leads to a 21.54% improvement over Prompt Pooling. Along with the benchmark, we establish a training pipeline that can be used for CL on code models, which we believe can motivate further development of CL methods for code models. Our code is available at https://github.com/amazon-science/codetaskcl-pptf
Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their remarkable performance on tasks such as code completion and editing, it is still unclear as to why. We help bridge this gap by exploring to what degree auto-regressive models understand the logical constructs of the underlying programs. We propose Counterfactual Analysis for Programming Concept Predicates (CACP) as a counterfactual testing framework to evaluate whether Large Code Models understand programming concepts. With only black-box access to the model, we use CACP to evaluate ten popular Large Code Models for four different programming concepts. Our findings suggest that current models lack understanding of concepts such as data flow and control flow.
In the scenario-based evaluation of machine learning models, a key problem is how to construct test datasets that represent various scenarios. The methodology proposed in this paper is to construct a benchmark and attach metadata to each test case. Then a test system can be constructed with test morphisms that filter the test cases based on metadata to form a dataset. The paper demonstrates this methodology with large language models for code generation. A benchmark called ScenEval is constructed from problems in textbooks, an online tutorial website and Stack Overflow. Filtering by scenario is demonstrated and the test sets are used to evaluate ChatGPT for Java code generation. Our experiments found that the performance of ChatGPT decreases with the complexity of the coding task. It is weakest for advanced topics like multi-threading, data structure algorithms and recursive methods. The Java code generated by ChatGPT tends to be much shorter than reference solution in terms of number of lines, while it is more likely to be more complex in both cyclomatic and cognitive complexity metrics, if the generated code is correct. However, the generated code is more likely to be less complex than the reference solution if the code is incorrect.
The recent improvement in code generation capabilities due to the use of large language models has mainly benefited general purpose programming languages. Domain specific languages, such as the ones used for IT Automation, have received far less attention, despite involving many active developers and being an essential component of modern cloud platforms. This work focuses on the generation of Ansible-YAML, a widely used markup language for IT Automation. We present Ansible Wisdom, a natural-language to Ansible-YAML code generation tool, aimed at improving IT automation productivity. Ansible Wisdom is a transformer-based model, extended by training with a new dataset containing Ansible-YAML. We also develop two novel performance metrics for YAML and Ansible to capture the specific characteristics of this domain. Results show that Ansible Wisdom can accurately generate Ansible script from natural language prompts with performance comparable or better than existing state of the art code generation models. In few-shot settings we asses the impact of training with Ansible, YAML data and compare with different baselines including Codex-Davinci-002. We also show that after finetuning, our Ansible specific model (BLEU: 66.67) can outperform a much larger Codex-Davinci-002 (BLEU: 50.4) model, which was evaluated in few shot settings.
Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, which primarily focus on accuracy, fall short in assessing the quality of the code generated by these models, specifically their tendency to produce code smells. To address this limitation, we introduce CodeSmellEval, a benchmark designed to evaluate the propensity of LLMs for generating code smells. Our benchmark includes a novel metric: Propensity Smelly Score (PSC), and a curated dataset of method-level code smells: CodeSmellData. To demonstrate the use of CodeSmellEval, we conducted a case study with two state-of-the-art LLMs, CodeLlama and Mistral. The results reveal that both models tend to generate code smells, such as simplifiable-condition and consider-merging-isinstance. These findings highlight the effectiveness of our benchmark in evaluating LLMs, providing valuable insights into their reliability and their propensity to introduce code smells in code generation tasks.
Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, \textbf{DiffuCoder}, on 130B tokens of code. Using this model as a testbed, we analyze its decoding behavior, revealing how it differs from that of AR models: (1) dLLMs can decide how causal their generation should be without relying on semi-AR decoding, and (2) increasing the sampling temperature diversifies not only token choices but also their generation order. This diversity creates a rich search space for RL rollouts. For RL training, to reduce the variance of token log-likelihood estimates and maintain training efficiency, we propose \textbf{coupled-GRPO}, a novel sampling scheme that constructs complementary mask noise for completions used in training. In our experiments, coupled-GRPO significantly improves DiffuCoder's performance on code generation benchmarks (+4.4\% on EvalPlus) and reduces reliance on AR causal during decoding. Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework. https://github.com/apple/ml-diffucoder.
Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains, including mitigating harm in LLM outputs, enhancing text summarization, and mathematical reasoning. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (<1B parameters) LLMs. We specifically focus on code generation tasks that require writing appropriate API calls, which is challenging due to the well-known issue of hallucination in LLMs. Our framework extracts AI feedback from a larger LLM (e.g., GPT-3.5) through a specialized prompting strategy and uses this data to train a reward model towards better alignment from smaller LLMs. We run our experiments on the Gorilla dataset and meticulously assess the quality of the model-generated code across various metrics, including AST, ROUGE, and Code-BLEU, and develop a pipeline to compute its executability rate accurately. Our approach significantly enhances the fine-tuned LLM baseline's performance, achieving a 4.5% improvement in executability rate. Notably, a smaller LLM model (780M parameters) trained with RLAIF surpasses a much larger fine-tuned baseline with 7B parameters, achieving a 1.0% higher code executability rate.
This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation attempts when the initial code generated by the LLM is inadequate. Generating computer programs in general-purpose programming languages like Python poses a challenge for LLMs when instructed to use code provided in the prompt. Code-specific LLMs (e.g., GitHub Copilot, CodeLlama2) can generate code completions in real-time by drawing on all code available in a development environment. However, restricting code-specific LLMs to use only in-context code is not straightforward, as the model is not explicitly instructed to use the user-provided code and users cannot highlight precisely which snippets of code the model should incorporate into its context. Moreover, current systems lack effective recovery methods, forcing users to iteratively re-prompt the model with modified prompts until a sufficient solution is reached. Our method differs from traditional LLM-powered code-generation by constraining code-generation to an explicit function set and enabling recovery from failed attempts through automatically generated sub-functions. When the LLM cannot produce working code, we generate modular sub-functions to aid subsequent attempts at generating functional code. A by-product of our method is a library of reusable sub-functions that can solve related tasks, imitating a software team where efficiency scales with experience. We also introduce a new "half-shot" evaluation paradigm that provides tighter estimates of LLMs' coding abilities compared to traditional zero-shot evaluation. Our proposed evaluation method encourages models to output solutions in a structured format, decreasing syntax errors that can be mistaken for poor coding ability.
Large Language Models (LLMs) excel in code-related tasks like code generation, but benchmark evaluations often overlook task characteristics, such as difficulty. Moreover, benchmarks are usually built using tasks described with one single prompt, despite the formulation of prompts having a profound impact on the outcome. This paper introduces a generalist approach, TaskEval, a framework using diverse prompts and Item Response Theory (IRT) to efficiently assess LLMs' capabilities and benchmark task characteristics, improving the understanding of their performance. Using two code generation benchmarks, HumanEval+ and ClassEval, as well as 5 code generation LLMs, we show that TaskEval is capable of characterizing the properties of tasks. Using topic analysis, we identify and analyze the tasks of respectively 17 and 21 topics within the benchmarks. We also cross-analyze tasks' characteristics with programming constructs (e.g., variable assignment, conditions, etc.) used by LLMs, emphasizing some patterns with tasks' difficulty. Finally, we conduct a comparison between the difficulty assessment of tasks by human-annotators and LLMs. Orthogonal to current benchmarking evaluation efforts, TaskEval can assist researchers and practitioners in fostering better assessments of LLMs. The tasks' characteristics can be used to identify shortcomings within existing benchmarks. This could be used to generate additional related tasks for the evaluation or improvement of LLM.
In software development, the user interface(UI) design process involves the part from an imagination that begins on a piece of paper where designers share thoughts to the final prototype that is ready to implement. UI designers use a technique of paper prototyping in low-fidelity sketches to implement the conceptual design. Once a design is drawn, it is usually captured within a photograph, then converted to a high-level mockup, and manually translated into a working client-side code by developers. The process consumes considerable effort and also delays the design process. Recently, researchers attempted to recreate UI from their sketches using code generation techniques. In this paper, we present a system for automatic code generation that combines recent advances in computer vision and deep learning for translating a sketched wireframe into a UI skeleton code. The proposed system has two main components: component recognition and code generation. The component recognition learns to extract visual features and their spatial layouts from sketched UI images. The code generator creates the equivalent UI skeleton codes based on the information from the detection model. A layout algorithm has been developed to resolve the overlapping of components and structure the layout. The evaluation result of the component recognition model indicates that the Faster R-CNN with Inception ResNet v2 backbone model achieved a mean average precision (mAP) of 95.5 %, among the other trained models. To evaluate the generator, we conducted a user study based on visual similarities between input image and the rendered UI.
Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good results. However, CodeAct greedily generates the next action's code block by relying on fragmented thoughts, resulting in inconsistency and instability. Moreover, CodeAct lacks action-related ground-truth (GT), making its supervision signals and termination conditions questionable in multi-turn interactions. To address these issues, we first introduce a simple yet effective end-to-end code generation paradigm, CodeProgram, which leverages code's systematic logic to align with global reasoning and enable cohesive problem-solving. Then, we propose Tree-of-Code (ToC), which self-grows CodeProgram nodes based on the executable nature of the code and enables self-supervision in a GT-free scenario. Experimental results on two datasets using ten popular zero-shot LLMs show ToC remarkably boosts accuracy by nearly 20% over CodeAct with less than 1/4 turns. Several LLMs even perform better on one-turn CodeProgram than on multi-turn CodeAct. To further investigate the trade-off between efficacy and efficiency, we test different ToC tree sizes and exploration mechanisms. We also highlight the potential of ToC's end-to-end data generation for supervised and reinforced fine-tuning.
This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis. Unlike existing datasets that are limited to either file-level RTL code or physical layout data, DeepCircuitX provides a holistic, multilevel resource that spans repository, file, module, and block-level RTL code. This structure enables more nuanced training and evaluation of large language models (LLMs) for RTL-specific tasks. DeepCircuitX is enriched with Chain of Thought (CoT) annotations, offering detailed descriptions of functionality and structure at multiple levels. These annotations enhance its utility for a wide range of tasks, including RTL code understanding, generation, and completion. Additionally, the dataset includes synthesized netlists and PPA metrics, facilitating early-stage design exploration and enabling accurate PPA prediction directly from RTL code. We demonstrate the dataset's effectiveness on various LLMs finetuned with our dataset and confirm the quality with human evaluations. Our results highlight DeepCircuitX as a critical resource for advancing RTL-focused machine learning applications in hardware design automation.Our data is available at https://zeju.gitbook.io/lcm-team.
Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we conduct an empirical study to identify a reasonable standard for "striking similarity" that excludes the possibility of independent creation, indicating a copy relationship between the LLM output and certain open-source code. Based on this standard, we propose LiCoEval, to evaluate the license compliance capabilities of LLMs, i.e., the ability to provide accurate license or copyright information when they generate code with striking similarity to already existing copyrighted code. Using LiCoEval, we evaluate 14 popular LLMs, finding that even top-performing LLMs produce a non-negligible proportion (0.88% to 2.01%) of code strikingly similar to existing open-source implementations. Notably, most LLMs fail to provide accurate license information, particularly for code under copyleft licenses. These findings underscore the urgent need to enhance LLM compliance capabilities in code generation tasks. Our study provides a foundation for future research and development to improve license compliance in AI-assisted software development, contributing to both the protection of open-source software copyrights and the mitigation of legal risks for LLM users.
Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding. Pursuant to achieving such technology, we introduce PyMT5, the Python method text-to-text transfer transformer, which is trained to translate between all pairs of Python method feature combinations: a single model that can both predict whole methods from natural language documentation strings (docstrings) and summarize code into docstrings of any common style. We present an analysis and modeling effort of a large-scale parallel corpus of 26 million Python methods and 7.7 million method-docstring pairs, demonstrating that for docstring and method generation, PyMT5 outperforms similarly-sized auto-regressive language models (GPT2) which were English pre-trained or randomly initialized. On the CodeSearchNet test set, our best model predicts 92.1% syntactically correct method bodies, achieved a BLEU score of 8.59 for method generation and 16.3 for docstring generation (summarization), and achieved a ROUGE-L F-score of 24.8 for method generation and 36.7 for docstring generation.
Generative AI (GenAI) has demonstrated remarkable capabilities in code generation, and its integration into complex product modeling and simulation code generation can significantly enhance the efficiency of the system design phase in Model-Based Systems Engineering (MBSE). In this study, we introduce a generative system design methodology framework for MBSE, offering a practical approach for the intelligent generation of simulation models for system physical properties. First, we employ inference techniques, generative models, and integrated modeling and simulation languages to construct simulation models for system physical properties based on product design documents. Subsequently, we fine-tune the language model used for simulation model generation on an existing library of simulation models and additional datasets generated through generative modeling. Finally, we introduce evaluation metrics for the generated simulation models for system physical properties. Our proposed approach to simulation model generation presents the innovative concept of scalable templates for simulation models. Using these templates, GenAI generates simulation models for system physical properties through code completion. The experimental results demonstrate that, for mainstream open-source Transformer-based models, the quality of the simulation model is significantly improved using the simulation model generation method proposed in this paper.
Large language models (LLMs) have demonstrated strong capabilities in code generation, underscoring the critical need for rigorous and comprehensive evaluation. Existing evaluation approaches fall into three categories, including human-centered, metric-based, and LLM-based. Considering that human-centered approaches are labour-intensive and metric-based ones overly rely on reference answers, LLM-based approaches are gaining increasing attention due to their stronger contextual understanding capabilities and superior efficiency. However, the performance of LLM-based approaches remains limited due to: (1) lack of multisource domain knowledge, and (2) insufficient comprehension of complex code. To mitigate the limitations, we propose CodeVisionary, the first LLM-based agent framework for evaluating LLMs in code generation. CodeVisionary consists of two stages: (1) Multiscore knowledge analysis stage, which aims to gather multisource and comprehensive domain knowledge by formulating and executing a stepwise evaluation plan. (2) Negotiation-based scoring stage, which involves multiple judges engaging in discussions to better comprehend the complex code and reach a consensus on the evaluation score. Extensive experiments demonstrate that CodeVisionary achieves the best performance for evaluating LLMs in code generation, outperforming the best baseline methods with average improvements of 0.202, 0.139, and 0.117 in Pearson, Spearman, and Kendall-Tau coefficients, respectively. Besides, CodeVisionary provides detailed evaluation reports, which assist developers in identifying shortcomings and making improvements. The resources of CodeVisionary are available at https://anonymous.4open.science/r/CodeVisionary.
Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always rely on auto-regressive decoding. However, previous methods using contrastive learning in neural text generation usually lead to inferior performance. In this paper, we analyse the underlying reasons and propose a new Contrastive Neural Text generation framework, CoNT. CoNT addresses bottlenecks that prevent contrastive learning from being widely adopted in generation tasks from three aspects -- the construction of contrastive examples, the choice of the contrastive loss, and the strategy in decoding. We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation. Experimental results show that CoNT clearly outperforms the conventional training framework on all the ten benchmarks with a convincing margin. Especially, CoNT surpasses previous the most competitive contrastive learning method for text generation, by 1.50 BLEU on machine translation and 1.77 ROUGE-1 on summarization, respectively. It achieves new state-of-the-art on summarization, code comment generation (without external data) and data-to-text generation.