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.
A code generation model generates code by taking a prompt from a code comment, existing code, or a combination of both. Although code generation models (e.g., GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test generation without fine-tuning for a strongly typed language like Java. To fill this gap, we investigated how well three models (Codex, GPT-3.5-Turbo, and StarCoder) can generate unit tests. We used two benchmarks (HumanEval and Evosuite SF110) to investigate the effect of context generation on the unit test generation process. We evaluated the models based on compilation rates, test correctness, test coverage, and test smells. We found that the Codex model achieved above 80% coverage for the HumanEval dataset, but no model had more than 2% coverage for the EvoSuite SF110 benchmark. The generated tests also suffered from test smells, such as Duplicated Asserts and Empty Tests.
For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of "outline-then-detail". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i.e. from coarse to fine in multiple passes. We first decompose source code into layout frame components and accessory components via abstract syntax tree parsing to construct a hierarchical representation. We then reform our prediction target into a multi-pass objective, each pass generates a subsequence, which is concatenated in the hierarchy. Finally, a tailored transformer architecture is leveraged to jointly encode the natural language descriptions and syntactically aligned I/O data samples. Extensive evaluations show that ChainCoder outperforms state-of-the-arts, demonstrating that our progressive generation eases the reasoning procedure and guides the language model to generate higher-quality solutions. Our codes are available at: https://github.com/VITA-Group/ChainCoder.
The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine intelligence and human knowledge by introducing a novel framework, which leverages the state-of-the-art large language models to develop ML solutions for novel tasks. We showcase the possibility of extending the capability of LLMs to comprehend structured inputs and perform thorough reasoning for solving novel ML tasks. And we find that, after some dedicated design, the LLM can (i) observe from the existing experiences of ML tasks and (ii) reason effectively to deliver promising results for new tasks. The solution generated can be used directly to achieve high levels of competitiveness. Examples and code available at https://github.com/microsoft/CoML.
Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine translation and summarization, their applicability in code intelligence tasks remains limited without human involvement. The complexity of programming concepts required for such tasks makes it difficult to develop evaluation metrics that align with human judgment. Token-matching-based metrics, such as BLEU, have demonstrated weak correlations with human practitioners in code intelligence tasks. Moreover, utilizing human-written test suites to evaluate functional correctness can be challenging in domains with low resources. To overcome these obstacles, we propose \texttt{ICE-Score}, a new evaluation metric via instructing large language models (LLMs) for code assessments. Our metric addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences, without the need for test oracles or references. We evaluate the efficacy of our metric on two different aspects (\textit{human preference} and \textit{execution success}) and four programming languages. Our results demonstrate that our metric surpasses state-of-the-art metrics for code generation, delivering high levels of accuracy and consistency across various programming languages and tasks. We also make our evaluation metric and datasets available to the public\footnote{\url{https://github.com/terryyz/ice-score}}, encouraging further research in evaluating code intelligence tasks.
Artificial intelligence (AI) tools based on large language models have acheived human-level performance on some computer programming tasks. We report several experiments using GPT-4 to generate computer code. These experiments demonstrate that AI code generation using the current generation of tools, while powerful, requires substantial human validation to ensure accurate performance. We also demonstrate that GPT-4 refactoring of existing code can significantly improve that code along several established metrics for code quality, and we show that GPT-4 can generate tests with substantial coverage, but that many of the tests fail when applied to the associated code. These findings suggest that while AI coding tools are very powerful, they still require humans in the loop to ensure validity and accuracy of the results.
The rise of large language models (LLMs) is revolutionizing information retrieval, question answering, summarization, and code generation tasks. However, in addition to confidently presenting factually inaccurate information at times (known as "hallucinations"), LLMs are also inherently limited by the number of input and output tokens that can be processed at once, making them potentially less effective on tasks that require processing a large set or continuous stream of information. A common approach to reducing the size of data is through lossless or lossy compression. Yet, in some cases it may not be strictly necessary to perfectly recover every detail from the original data, as long as a requisite level of semantic precision or intent is conveyed. This paper presents three contributions to research on LLMs. First, we present the results from experiments exploring the viability of approximate compression using LLMs, focusing specifically on GPT-3.5 and GPT-4 via ChatGPT interfaces. Second, we investigate and quantify the capability of LLMs to compress text and code, as well as to recall and manipulate compressed representations of prompts. Third, we present two novel metrics -- Exact Reconstructive Effectiveness (ERE) and Semantic Reconstruction Effectiveness (SRE) -- that quantify the level of preserved intent between text compressed and decompressed by the LLMs we studied. Our initial results indicate that GPT-4 can effectively compress and reconstruct text while preserving the semantic essence of the original text, providing a path to leverage $\sim$5$\times$ more tokens than present limits allow.
Recently, the ChatGPT LLM has received great attention: it can be used as a bot for discussing source code, prompting it to suggest changes, provide descriptions or even generate code. Typical demonstrations generally focus on existing benchmarks, which may have been used in model training (i.e., data leakage). To assess the feasibility of using an LLM as a useful assistant bot for programmers, we must assess its realistic capabilities on unseen problems as well as its capabilities on various tasks. In this paper, we present an empirical study of ChatGPT's potential as a fully automated programming assistant, focusing on the tasks of code generation, program repair, and code summariziation. The study investigates ChatGPT's performance on common programming problems and compares it with state-of-the-art approaches on two benchmarks. Among several findings, our study shows that ChatGPT is effective in dealing with common programming problems. However, our experiments also reveal limitations in terms of its attention span: detailed descriptions will constrain the focus of ChatGPT and prevent it from leveraging its vast knowledge to solve the actual problem. Surprisingly, we have identified the ability of ChatGPT to reason the original intention of the code. We expect future work to build on this insight for dealing with the open question of the oracle problem. Our findings contribute interesting insights to the development of LLMs for programming assistance, notably by demonstrating the importance of prompt engineering, and providing a better understanding of ChatGPT's practical applications for software engineering.
Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in language modeling for long text generation, and one proposed solution is the use of a latent stochastic process. This approach involves generating a document plan and then producing text that is consistent with it. In this study, we investigate whether this technique can be applied to code generation to improve coherence. We base our proposed encoder and decoder on the pre-trained GPT-2 based CodeParrot model and utilize the APPS dataset for training. We evaluate our results using the HumanEval benchmark and observe that the modified Time Control model performs similarly to CodeParrot on this evaluation.
The digital transformation of automation places new demands on data acquisition and processing in industrial processes. Logical relationships between acquired data and cyclic process sequences must be correctly interpreted and evaluated. To solve this problem, a novel approach based on evolutionary algorithms is proposed to self optimise the system logic of complex processes. Based on the genetic results, a programme code for the system implementation is derived by decoding the solution. This is achieved by a flexible system structure with an upstream, intermediate and downstream unit. In the intermediate unit, a directed learning process interacts with a system replica and an evaluation function in a closed loop. The code generation strategy is represented by redundancy and priority, sequencing and performance derivation. The presented approach is evaluated on an industrial liquid station process subject to a multi-objective optimisation problem.
Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair approaches to improve code generation performance. In this work, we propose Self-Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations. In particular, we demonstrate that Self-Debugging can teach the large language model to perform rubber duck debugging; i.e., without any human feedback on the code correctness or error messages, the model is able to identify its mistakes by investigating the execution results and explaining the generated code in natural language. Self-Debugging achieves the state-of-the-art performance on several code generation benchmarks, including the Spider dataset for text-to-SQL generation, TransCoder for C++-to-Python translation, and MBPP for text-to-Python generation. On the Spider benchmark where there are no unit tests to verify the correctness of predictions, Self-Debugging with code explanation consistently improves the baseline by 2-3%, and improves the prediction accuracy on problems of the hardest level by 9%. On TransCoder and MBPP where unit tests are available, Self-Debugging improves the baseline accuracy by up to 12%. Meanwhile, by leveraging feedback messages and reusing failed predictions, Self-Debugging notably improves sample efficiency, and can match or outperform baseline models that generate more than 10x candidate programs.
Although code generation for Convolution Neural Network (CNN) models has been extensively studied, performing efficient data slicing and parallelization for highly-constrai\-ned Multicore Neural Processor Units (NPUs) is still a challenging problem. Given the size of convolutions' input/output tensors and the small footprint of NPU on-chip memories, minimizing memory transactions while maximizing parallelism and MAC utilization are central to any effective solution. This paper proposes a TensorFlow XLA/LLVM compiler optimization pass for Multicore NPUs, called Tensor Slicing Optimization (TSO), which: (a) maximizes convolution parallelism and memory usage across NPU cores; and (b) reduces data transfers between host and NPU on-chip memories by using DRAM memory burst time estimates to guide tensor slicing. To evaluate the proposed approach, a set of experiments was performed using the NeuroMorphic Processor (NMP), a multicore NPU containing 32 RISC-V cores extended with novel CNN instructions. Experimental results show that TSO is capable of identifying the best tensor slicing that minimizes execution time for a set of CNN models. Speed-ups of up to 21.7\% result when comparing the TSO burst-based technique to a no-burst data slicing approach. To validate the generality of the TSO approach, the algorithm was also ported to the Glow Machine Learning framework. The performance of the models were measured on both Glow and TensorFlow XLA/LLVM compilers, revealing similar results.
Recent developments in deep learning have resulted in code-generation models that produce source code from natural language and code-based prompts with high accuracy. This is likely to have profound effects in the classroom, where novices learning to code can now use free tools to automatically suggest solutions to programming exercises and assignments. However, little is currently known about how novices interact with these tools in practice. We present the first study that observes students at the introductory level using one such code auto-generating tool, Github Copilot, on a typical introductory programming (CS1) assignment. Through observations and interviews we explore student perceptions of the benefits and pitfalls of this technology for learning, present new observed interaction patterns, and discuss cognitive and metacognitive difficulties faced by students. We consider design implications of these findings, specifically in terms of how tools like Copilot can better support and scaffold the novice programming experience.
Large Language Models (LLMs) have shown great success in code generation. LLMs take as the input a prompt and output the code. A key question is how to make prompts (i.e., Prompting Techniques). Existing prompting techniques are designed for natural language generation and have low accuracy in code generation. In this paper, we propose a new prompting technique named AceCoder. Our motivation is that code generation meets two unique challenges (i.e., requirement understanding and code implementation). AceCoder contains two novel mechanisms (i.e., guided code generation and example retrieval) to solve these challenges. (1) Guided code generation asks LLMs first to analyze requirements and output an intermediate preliminary (e.g., test cases). The preliminary is used to clarify requirements and tell LLMs "what to write". (2) Example retrieval selects similar programs as examples in prompts, which provide lots of relevant content (e.g., algorithms, APIs) and teach LLMs "how to write". We apply AceCoder to three LLMs (e.g., Codex) and evaluate it on three public benchmarks using the Pass@k. Results show that AceCoder can significantly improve the performance of LLMs on code generation. (1) In terms of Pass@1, AceCoder outperforms the state-of-the-art baseline by up to 56.4% in MBPP, 70.7% in MBJP, and 88.4% in MBJSP. (2) AceCoder is effective in LLMs with different sizes (i.e., 6B to 13B) and different languages (i.e., Python, Java, and JavaScript). (3) Human evaluation shows human developers prefer programs from AceCoder.
Large pre-trained code generation models, such as OpenAI Codex, can generate syntax- and function-correct code, making the coding of programmers more productive and our pursuit of artificial general intelligence closer. In this paper, we introduce CodeGeeX, a multilingual model with 13 billion parameters for code generation. CodeGeeX is pre-trained on 850 billion tokens of 23 programming languages as of June 2022. Our extensive experiments suggest that CodeGeeX outperforms multilingual code models of similar scale for both the tasks of code generation and translation on HumanEval-X. Building upon HumanEval (Python only), we develop the HumanEval-X benchmark for evaluating multilingual models by hand-writing the solutions in C++, Java, JavaScript, and Go. In addition, we build CodeGeeX-based extensions on Visual Studio Code, JetBrains, and Cloud Studio, generating 4.7 billion tokens for tens of thousands of active users per week. Our user study demonstrates that CodeGeeX can help to increase coding efficiency for 83.4% of its users. Finally, CodeGeeX is publicly accessible and in Sep. 2022, we open-sourced its code, model weights (the version of 850B tokens), API, extensions, and HumanEval-X at https://github.com/THUDM/CodeGeeX.
There are plenty of graph neural network (GNN) accelerators being proposed. However, they highly rely on users' hardware expertise and are usually optimized for one specific GNN model, making them challenging for practical use. Therefore, in this work, we propose GNNBuilder, the first automated, generic, end-to-end GNN accelerator generation framework. It features four advantages: (1) GNNBuilder can automatically generate GNN accelerators for a wide range of GNN models arbitrarily defined by users; (2) GNNBuilder takes standard PyTorch programming interface, introducing zero overhead for algorithm developers; (3) GNNBuilder supports end-to-end code generation, simulation, accelerator optimization, and hardware deployment, realizing a push-button fashion for GNN accelerator design; (4) GNNBuilder is equipped with accurate performance models of its generated accelerator, enabling fast and flexible design space exploration (DSE). In the experiments, first, we show that our accelerator performance model has errors within $36\%$ for latency prediction and $18\%$ for BRAM count prediction. Second, we show that our generated accelerators can outperform CPU by $6.33\times$ and GPU by $6.87\times$. This framework is open-source, and the code is available at https://github.com/sharc-lab/gnn-builder.
Artificial Intelligence (AI) has made incredible progress recently. On the one hand, advanced foundation models like ChatGPT can offer powerful conversation, in-context learning and code generation abilities on a broad range of open-domain tasks. They can also generate high-level solution outlines for domain-specific tasks based on the common sense knowledge they have acquired. However, they still face difficulties with some specialized tasks because they lack enough domain-specific data during pre-training or they often have errors in their neural network computations on those tasks that need accurate executions. On the other hand, there are also many existing models and systems (symbolic-based or neural-based) that can do some domain-specific tasks very well. However, due to the different implementation or working mechanisms, they are not easily accessible or compatible with foundation models. Therefore, there is a clear and pressing need for a mechanism that can leverage foundation models to propose task solution outlines and then automatically match some of the sub-tasks in the outlines to the off-the-shelf models and systems with special functionalities to complete them. Inspired by this, we introduce TaskMatrix.AI as a new AI ecosystem that connects foundation models with millions of APIs for task completion. Unlike most previous work that aimed to improve a single AI model, TaskMatrix.AI focuses more on using existing foundation models (as a brain-like central system) and APIs of other AI models and systems (as sub-task solvers) to achieve diversified tasks in both digital and physical domains. As a position paper, we will present our vision of how to build such an ecosystem, explain each key component, and use study cases to illustrate both the feasibility of this vision and the main challenges we need to address next.
The potential for pre-trained large language models (LLMs) to use natural language feedback at inference time has been an exciting recent development. We build upon this observation by formalizing an algorithm for learning from natural language feedback at training time instead, which we call Imitation learning from Language Feedback (ILF). ILF requires only a small amount of human-written feedback during training and does not require the same feedback at test time, making it both user-friendly and sample-efficient. We further show that ILF can be seen as a form of minimizing the KL divergence to the ground truth distribution and demonstrate a proof-of-concept on a neural program synthesis task. We use ILF to improve a Codegen-Mono 6.1B model's pass@1 rate by 38% relative (and 10% absolute) on the Mostly Basic Python Problems (MBPP) benchmark, outperforming both fine-tuning on MBPP and fine-tuning on repaired programs written by humans. Overall, our results suggest that learning from human-written natural language feedback is both more effective and sample-efficient than training exclusively on demonstrations for improving an LLM's performance on code generation tasks.
Large Language Models (LLMs), such as GPT-3, have demonstrated remarkable natural language processing and generation capabilities and have been applied to a variety tasks, such as source code generation. This paper explores the potential of integrating LLMs in the hazard analysis for safety-critical systems, a process which we refer to as co-hazard analysis (CoHA). In CoHA, a human analyst interacts with an LLM via a context-aware chat session and uses the responses to support elicitation of possible hazard causes. In this experiment, we explore CoHA with three increasingly complex versions of a simple system, using Open AI's ChatGPT service. The quality of ChatGPT's responses were systematically assessed to determine the feasibility of CoHA given the current state of LLM technology. The results suggest that LLMs may be useful for supporting human analysts performing hazard analysis.
This paper presents the first comprehensive analysis of ChatGPT's Text-to-SQL ability. Given the recent emergence of large-scale conversational language model ChatGPT and its impressive capabilities in both conversational abilities and code generation, we sought to evaluate its Text-to-SQL performance. We conducted experiments on 12 benchmark datasets with different languages, settings, or scenarios, and the results demonstrate that ChatGPT has strong text-to-SQL abilities. Although there is still a gap from the current state-of-the-art (SOTA) model performance, considering that the experiment was conducted in a zero-shot scenario, ChatGPT's performance is still impressive. Notably, in the ADVETA (RPL) scenario, the zero-shot ChatGPT even outperforms the SOTA model that requires fine-tuning on the Spider dataset by 4.1\%, demonstrating its potential for use in practical applications. To support further research in related fields, we have made the data generated by ChatGPT publicly available at https://github.com/THU-BPM/chatgpt-sql.