In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored. To address this gap, we propose complexity-impacted reasoning score (CIRS), which combines structural and logical attributes, to measure the correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity by considering the difficulty and the cyclomatic complexity. Through an empirical analysis, we find not all code data of complexity can be learned or understood by LLMs. Optimal level of complexity is critical to the improvement of reasoning abilities by program-aided prompting. Then we design an auto-synthesizing and stratifying algorithm, and apply it to instruction generation for mathematical reasoning and code data filtering for code generation tasks. Extensive results demonstrates the effectiveness of our proposed approach. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
Large language models (LLMs) have significantly improved the ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that toplevel software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, I argue that the same should be applied to LLMs for code generation tasks. By asking probing questions in various topics before generating the final code, the challenges of programming with LLMs, such as unclear intent specification, lack of computational thinking, and undesired code quality, may be alleviated. This, in turn, increases confidence in the generated code. In this work, I explore how to leverage better communication skills to achieve greater confidence in generated code. I propose a communication-centered process that uses an LLM-generated communicator to identify issues with high ambiguity or low confidence in problem descriptions and generated code. I then ask clarifying questions to obtain responses from users for refining the code.
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide multiple flavors to cover a wide range of applications: foundation models (Code Llama), Python specializations (Code Llama - Python), and instruction-following models (Code Llama - Instruct) with 7B, 13B, 34B and 70B parameters each. All models are trained on sequences of 16k tokens and show improvements on inputs with up to 100k tokens. 7B, 13B and 70B Code Llama and Code Llama - Instruct variants support infilling based on surrounding content. Code Llama reaches state-of-the-art performance among open models on several code benchmarks, with scores of up to 67% and 65% on HumanEval and MBPP, respectively. Notably, Code Llama - Python 7B outperforms Llama 2 70B on HumanEval and MBPP, and all our models outperform every other publicly available model on MultiPL-E. We release Code Llama under a permissive license that allows for both research and commercial use.
One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. Although a number of studies have shown that LLMs have been effectively evaluated on popular accuracy metrics (e.g., BLEU, CodeBleu), previous research has largely overlooked the role of Causal Inference as a fundamental component of the interpretability of LLMs' performance. Existing benchmarks and datasets are meant to highlight the difference between the expected and the generated outcome, but do not take into account confounding variables (e.g., lines of code, prompt size) that equally influence the accuracy metrics. The fact remains that, when dealing with generative software tasks by LLMs, no benchmark is available to tell researchers how to quantify neither the causal effect of SE-based treatments nor the correlation of confounders to the model's performance. In an effort to bring statistical rigor to the evaluation of LLMs, this paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks (i.e., code completion, code summarization, and commit generation) to help aid the interpretation of LLMs' performance. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods. The results of the case study demonstrate the positive causal influence of prompt semantics on ChatGPT's generative performance by an average treatment effect of $\approx 3\%$. Moreover, it was found that confounders such as prompt size are highly correlated with accuracy metrics ($\approx 0.412\%$). The end result of our case study is to showcase causal inference evaluations, in practice, to reduce confounding bias. By reducing the bias, we offer an interpretable solution for the accuracy metric under analysis.
Biometric applications, such as person re-identification (ReID), are often deployed on energy constrained devices. While recent ReID methods prioritize high retrieval performance, they often come with large computational costs and high search time, rendering them less practical in real-world settings. In this work, we propose an input-adaptive network with multiple exit blocks, that can terminate computation early if the retrieval is straightforward or noisy, saving a lot of computation. To assess the complexity of the input, we introduce a temporal-based classifier driven by a new training strategy. Furthermore, we adopt a binary hash code generation approach instead of relying on continuous-valued features, which significantly improves the search process by a factor of 20. To ensure similarity preservation, we utilize a new ranking regularizer that bridges the gap between continuous and binary features. Extensive analysis of our proposed method is conducted on three datasets: Market1501, MSMT17 (Multi-Scene Multi-Time), and the BGC1 (BRIAR Government Collection). Using our approach, more than 70% of the samples with compact hash codes exit early on the Market1501 dataset, saving 80% of the networks computational cost and improving over other hash-based methods by 60%. These results demonstrate a significant improvement over dynamic networks and showcase comparable accuracy performance to conventional ReID methods. Code will be made available.
Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of fine-tuning LLMs, this process incurs high computational costs, making it impractical in resource-scarce environments, particularly for models with billions of parameters. To address these challenges, previous research explored in-context learning (ICL) and retrieval-augmented generation (RAG) as strategies to guide the LLM generative process with task-specific prompt examples. However, ICL and RAG introduce inconveniences, such as the need for designing contextually relevant prompts and the absence of learning task-specific parameters, thereby limiting downstream task performance. In this context, we foresee parameter-efficient fine-tuning (PEFT) as a promising approach to efficiently specialize LLMs to task-specific data while maintaining reasonable resource consumption. In this paper, we deliver a comprehensive study of PEFT techniques for LLMs in the context of automated code generation. Our comprehensive investigation of PEFT techniques for LLMs reveals their superiority and potential over ICL and RAG across a diverse set of LLMs and three representative Python code generation datasets: Conala, CodeAlpacaPy, and APPS. Furthermore, our study highlights the potential for tuning larger LLMs and significant reductions in memory usage by combining PEFT with quantization. Therefore, this study opens opportunities for broader applications of PEFT in software engineering scenarios. Our code is available at https://github.com/martin-wey/peft-llm-code/.
Large Language Models(LLMs) have been attracting attention due to a ability called in-context learning(ICL). ICL, without updating the parameters of a LLM, it is possible to achieve highly accurate inference based on rules ``in the context'' by merely inputting a training data into the prompt. Although ICL is a developing field with many unanswered questions, LLMs themselves serves as a inference model, seemingly realizing inference without explicitly indicate ``inductive bias''. On the other hand, a code generation is also a highlighted application of LLMs. The accuracy of code generation has dramatically improved, enabling even non-engineers to generate code to perform the desired tasks by crafting appropriate prompts. In this paper, we propose a novel ``learning'' method called an ``Inductive-Bias Learning (IBL)'', which combines the techniques of ICL and code generation. An idea of IBL is straightforward. Like ICL, IBL inputs a training data into the prompt and outputs a code with a necessary structure for inference (we referred to as ``Code Model'') from a ``contextual understanding''. Despite being a seemingly simple approach, IBL encompasses both a ``property of inference without explicit inductive bias'' inherent in ICL and a ``readability and explainability'' of the code generation. Surprisingly, generated Code Models have been found to achieve predictive accuracy comparable to, and in some cases surpassing, ICL and representative machine learning models. Our IBL code is open source: https://github.com/fuyu-quant/IBLM
Recently, the large language models (LLMs) have shown extraordinary ability in understanding natural language and generating programming code. It has been a common practice of software engineers to consult LLMs when encountering coding questions. Although efforts have been made to avoid syntax errors and align the code with the intended semantics, the reliability and robustness of the code generationfrom LLMs have not yet been thoroughly studied. The executable code is not equivalent to the reliable and robust code, especially in the context of real-world software development. The misuse of APIs in the generated code could lead to severe problem, such as resource leaks, program crashes. To make things worse, the users of LLM code generation services are actually the developers that are most vulnerable to these code that seems right -- They are always novice developers that are not familiar with the APIs that LLMs generate code for them. Therefore, they could hardly tell the misuse in the code generated by LLMs, which further facilitates the incorrect code applied in real-world software. Existing code evaluation benchmark and datasets focus on crafting small tasks such as programming questions in coding interviews, which however deviates from the problem that developers would ask LLM for real-world coding help. To fill the missing piece, in this work, we propose a dataset RobustAPI for evaluating the reliability and robustness of code generated by LLMs. We collect 1208 coding questions from StackOverflow on 24 representative Java APIs. We summarize thecommon misuse patterns of these APIs and evaluate them oncurrent popular LLMs. The evaluation results show that evenfor GPT-4, 62% of the generated code contains API misuses,which would cause unexpected consequences if the code isintroduced into real-world software.
Chain-of-thought (CoT) has emerged as a groundbreaking tool in NLP, notably for its efficacy in complex reasoning tasks, such as mathematical proofs. However, its application in code generation faces a distinct challenge, i.e., although the code generated with CoT reasoning is logically correct, it faces the problem of syntax error (e.g., invalid syntax error report) during code execution, which causes the CoT result's pass@1 in HumanEval even lower than the zero-shot result. In this paper, we present Code Chain-of-Thought (CodeCoT) that integrates CoT with a self-examination process for code generation. CodeCoT begins with the LLMs using CoT for initial code development to ensure the generated code follows the correct logic flow. Then, CodeCoT will generate test cases to validate whether the code has syntax errors during the execution. CodeCoT then employs a self-examination phase, in which the generated code is executed against these test cases in the local environment. If the local environment raises error information (e.g., invalid syntax error), CodeCoT will iteratively refine the code based on the feedback information. Within this loop, CodeCoT can make sure their generated codes not only follow the logic flow of the code description, but the syntax error will also be addressed with the self-examination process. Our evaluation results reveal that CodeCoT improves the effectiveness of code generation. For example, CodeCoT increases pass@1 from 75.6% to 79.3% for the HumanEval dataset.
Finetuning large language models (LLMs) on instructions leads to vast performance improvements on natural language tasks. We apply instruction tuning using code, leveraging the natural structure of Git commits, which pair code changes with human instructions. We compile CommitPack: 4 terabytes of Git commits across 350 programming languages. We benchmark CommitPack against other natural and synthetic code instructions (xP3x, Self-Instruct, OASST) on the 16B parameter StarCoder model, and achieve state-of-the-art performance among models not trained on OpenAI outputs, on the HumanEval Python benchmark (46.2% pass@1). We further introduce HumanEvalPack, expanding the HumanEval benchmark to a total of 3 coding tasks (Code Repair, Code Explanation, Code Synthesis) across 6 languages (Python, JavaScript, Java, Go, C++, Rust). Our models, OctoCoder and OctoGeeX, achieve the best performance across HumanEvalPack among all permissive models, demonstrating CommitPack's benefits in generalizing to a wider set of languages and natural coding tasks. Code, models and data are freely available at https://github.com/bigcode-project/octopack.
AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub, HuggingFace). As a consequence, AI models become an easy target for data poisoning, i.e., an attack that injects malicious samples into the training data to generate vulnerable code. To address this threat, this work investigates the security of AI code generators by devising a targeted data poisoning strategy. We poison the training data by injecting increasing amounts of code containing security vulnerabilities and assess the attack's success on different state-of-the-art models for code generation. Our study shows that AI code generators are vulnerable to even a small amount of poison. Notably, the attack success strongly depends on the model architecture and poisoning rate, whereas it is not influenced by the type of vulnerabilities. Moreover, since the attack does not impact the correctness of code generated by pre-trained models, it is hard to detect. Lastly, our work offers practical insights into understanding and potentially mitigating this threat.
The aim of this study is to evaluate the performance of AI-assisted programming in actual mobile development teams that are focused on native mobile languages like Kotlin and Swift. The extensive case study involves 16 participants and 2 technical reviewers, from a software development department designed to understand the impact of using LLMs trained for code generation in specific phases of the team, more specifically, technical onboarding and technical stack switch. The study uses technical problems dedicated to each phase and requests solutions from the participants with and without using AI-Code generators. It measures time, correctness, and technical integration using ReviewerScore, a metric specific to the paper and extracted from actual industry standards, the code reviewers of merge requests. The output is converted and analyzed together with feedback from the participants in an attempt to determine if using AI-assisted programming tools will have an impact on getting developers onboard in a project or helping them with a smooth transition between the two native development environments of mobile development, Android and iOS. The study was performed between May and June 2023 with members of the mobile department of a software development company based in Cluj-Napoca, with Romanian ownership and management.
Large Language Models (LLMs) are advanced Artificial Intelligence (AI) systems that have undergone extensive training using large datasets in order to understand and produce language that closely resembles that of humans. These models have reached a level of proficiency where they are capable of successfully completing university exams across several disciplines and generating functional code to handle novel problems. This research investigates the coding proficiency of ChatGPT 3.5, a LLM released by OpenAI in November 2022, which has gained significant recognition for its impressive text generating and code creation capabilities. The skill of the model in creating code snippets is evaluated across 10 various programming languages and 4 different software domains. Based on the findings derived from this research, major unexpected behaviors and limitations of the model have been identified. This study aims to identify potential areas for development and examine the ramifications of automated code generation on the evolution of programming languages and on the tech industry.
The introduction of large language models (LLMs) like ChatGPT and Google Palm2 for smart contract generation seems to be the first well-established instance of an AI pair programmer. LLMs have access to a large number of open-source smart contracts, enabling them to utilize more extensive code in Solidity than other code generation tools. Although the initial and informal assessments of LLMs for smart contract generation are promising, a systematic evaluation is needed to explore the limits and benefits of these models. The main objective of this study is to assess the quality of generated code provided by LLMs for smart contracts. We also aim to evaluate the impact of the quality and variety of input parameters fed to LLMs. To achieve this aim, we created an experimental setup for evaluating the generated code in terms of validity, correctness, and efficiency. Our study finds crucial evidence of security bugs getting introduced in the generated smart contracts as well as the overall quality and correctness of the code getting impacted. However, we also identified the areas where it can be improved. The paper also proposes several potential research directions to improve the process, quality and safety of generated smart contract codes.
In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100 class-level Python code generation tasks with approximately 500 person-hours. Based on it, we then perform the first study of 11 state-of-the-art LLMs on class-level code generation. Based on our results, we have the following main findings. First, we find that all existing LLMs show much worse performance on class-level code generation compared to on standalone method-level code generation benchmarks like HumanEval; and the method-level coding ability cannot equivalently reflect the class-level coding ability among LLMs. Second, we find that GPT-4 and GPT-3.5 still exhibit dominate superior than other LLMs on class-level code generation, and the second-tier models includes Instruct-Starcoder, Instruct-Codegen, and Wizardcoder with very similar performance. Third, we find that generating the entire class all at once (i.e. holistic generation strategy) is the best generation strategy only for GPT-4 and GPT-3.5, while method-by-method generation (i.e. incremental and compositional) is better strategies for the other models with limited ability of understanding long instructions and utilizing the middle information. Lastly, we find the limited model ability of generating method-dependent code and discuss the frequent error types in generated classes. Our benchmark is available at https://github.com/FudanSELab/ClassEval.
In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by generating high-quality Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increase. Upon testing with a more diverse and complex problem set, we find that the fine-tuned model shows competitive performance against state-of-the-art gpt-3.5-turbo, excelling in certain scenarios. Notably, it demonstrates a 41% improvement in generating syntactically correct Verilog code across various problem categories compared to its pre-trained counterpart, highlighting the potential of smaller, in-house LLMs in hardware design automation.
Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT
This paper presents an AI-assisted programming tool called Copilot for Xcode for program composition and design to support human software developers. By seamlessly integrating cloud-based Large Language Models (LLM) with Apple's local development environment, Xcode, this tool enhances productivity and unleashes creativity for software development in Apple software ecosystem (e.g., iOS apps, macOS). Leveraging advanced natural language processing (NLP) techniques, Copilot for Xcode effectively processes source code tokens and patterns within code repositories, enabling features such as code generation, autocompletion, documentation, and error detection. Software developers can also query and make "small" decisions for program composition, some of which can be made simultaneously, and this is facilitated through prompt engineering in a chat interface of Copilot for Xcode. Finally, we present simple case studies as evidence of the effectiveness of utilizing NLP in Xcode to prompt popular LLM services like OpenAI ChatGPT for program composition and design.
Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.
The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of tasks now face an increasing risk of containing factual errors when handled by generative models. (2) Generated texts tend to be lengthy and lack a clearly defined granularity for individual facts. (3) There is a scarcity of explicit evidence available during the process of fact checking. With the above challenges in mind, in this paper, we propose FacTool, a task and domain agnostic framework for detecting factual errors of texts generated by large language models (e.g., ChatGPT). Experiments on four different tasks (knowledge-based QA, code generation, mathematical reasoning, and scientific literature review) show the efficacy of the proposed method. We release the code of FacTool associated with ChatGPT plugin interface at https://github.com/GAIR-NLP/factool .