arXiv subjects

Zhi Jin

Publications and source records attributed to Zhi Jin.

At least 145 records · Page 8Linked to original sources

arXiv2024

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. (1) DevEval aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). (3) DevEval comprises 1,874 testing samples from 117 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, in our experiments, the highest Pass@1 of gpt-4-turbo is only 53.04%. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released.

cs.CL↗

arXiv2024

Systematic Literature Review of Commercial Participation in Open Source Software

Open source software (OSS) has been playing a fundamental role in not only information technology but also our social lives. Attracted by various advantages of OSS, increasing commercial companies take extensive participation in open source development and have had a broad impact. This paper provides a comprehensive systematic literature review (SLR) of existing research on company participation in OSS. We collected 92 papers and organized them based on their research topics, which cover three main directions, i.e., participation motivation, contribution model, and impact on OSS development. We found the explored motivations of companies are mainly from economic, technological, and social aspects. Existing studies categorize companies' contribution models in OSS projects mainly through their objectives and how they shape OSS communities. Researchers also explored how commercial participation affects OSS development. We conclude with research challenges and promising research directions on commercial participation in OSS. This study contributes to a comprehensive understanding of commercial participation in OSS development.

cs.SE↗

arXiv2024

PACE: Improving Prompt with Actor-Critic Editing for Large Language Model

Large language models (LLMs) have showcased remarkable potential across various tasks by conditioning on prompts. However, the quality of different human-written prompts leads to substantial discrepancies in LLMs' performance, and improving prompts usually necessitates considerable human effort and expertise. To this end, this paper proposes Prompt with Actor-Critic Editing (PACE) for LLMs to enable automatic prompt editing. Drawing inspiration from the actor-critic algorithm in reinforcement learning, PACE leverages LLMs as the dual roles of actors and critics, conceptualizing prompt as a type of policy. PACE refines prompt, taking into account the feedback from both actors performing prompt and critics criticizing response. This process helps LLMs better align prompt to a specific task, thanks to real responses and thinking from LLMs. We conduct extensive experiments on 24 instruction induction tasks and 21 big-bench tasks. Experimental results indicate that PACE elevates the relative performance of medium/low-quality human-written prompts by up to 98\%, which has comparable performance to high-quality human-written prompts. Moreover, PACE also exhibits notable efficacy for prompt generation.

cs.CL↗

arXiv2024

Self-collaboration Code Generation via ChatGPT

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that significantly controls development complexity and enhances software quality. Inspired by this, we present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. Specifically, through role instructions, 1) Multiple LLM agents act as distinct `experts', each responsible for a specific subtask within a complex task; 2) Specify the way to collaborate and interact, so that different roles form a virtual team to facilitate each other's work, ultimately the virtual team addresses code generation tasks collaboratively without the need for human intervention. To effectively organize and manage this virtual team, we incorporate software-development methodology into the framework. Thus, we assemble an elementary team consisting of three LLM roles (i.e., analyst, coder, and tester) responsible for software development's analysis, coding, and testing stages. We conduct comprehensive experiments on various code-generation benchmarks. Experimental results indicate that self-collaboration code generation relatively improves 29.9%-47.1% Pass@1 compared to the base LLM agent. Moreover, we showcase that self-collaboration could potentially enable LLMs to efficiently handle complex repository-level tasks that are not readily solved by the single LLM agent.

cs.SE↗

arXiv2024

Exploring and Unleashing the Power of Large Language Models in Automated Code Translation

Code translation tools (transpilers) are developed for automatic source-to-source translation. Although learning-based transpilers have shown impressive enhancement against rule-based counterparts, owing to their task-specific pre-training on extensive monolingual corpora. Their current performance still remains unsatisfactory for practical deployment, and the associated training resources are also prohibitively expensive. LLMs pre-trained on huge amounts of human-written code/text have shown remarkable performance in many code intelligence tasks due to their powerful generality, even without task-specific training. Thus, LLMs can potentially circumvent the above limitations, but they have not been exhaustively explored yet. This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs, missing clear instructions on I/O types in translation, and ignoring discrepancies between source and target programs. Enlightened by the above findings, we further propose UniTrans, a Unified code Translation framework, applicable to various LLMs, for unleashing their power in this field. Specifically, UniTrans first crafts a series of test cases for target programs with the assistance of source programs. Next, it harnesses the above auto-generated test cases to augment the code translation and then evaluate their correctness via execution. Afterward, UniTrans further (iteratively) repairs incorrectly translated programs prompted by test case execution results. Extensive experiments are conducted on six settings of translation datasets between Python, Java, and C++. Three recent LLMs of diverse sizes are tested with UniTrans, and all achieve substantial improvements.

cs.SE↗

arXiv2024

FastScene: Text-Driven Fast 3D Indoor Scene Generation via Panoramic Gaussian Splatting

Text-driven 3D indoor scene generation holds broad applications, ranging from gaming and smart homes to AR/VR applications. Fast and high-fidelity scene generation is paramount for ensuring user-friendly experiences. However, existing methods are characterized by lengthy generation processes or necessitate the intricate manual specification of motion parameters, which introduces inconvenience for users. Furthermore, these methods often rely on narrow-field viewpoint iterative generations, compromising global consistency and overall scene quality. To address these issues, we propose FastScene, a framework for fast and higher-quality 3D scene generation, while maintaining the scene consistency. Specifically, given a text prompt, we generate a panorama and estimate its depth, since the panorama encompasses information about the entire scene and exhibits explicit geometric constraints. To obtain high-quality novel views, we introduce the Coarse View Synthesis (CVS) and Progressive Novel View Inpainting (PNVI) strategies, ensuring both scene consistency and view quality. Subsequently, we utilize Multi-View Projection (MVP) to form perspective views, and apply 3D Gaussian Splatting (3DGS) for scene reconstruction. Comprehensive experiments demonstrate FastScene surpasses other methods in both generation speed and quality with better scene consistency. Notably, guided only by a text prompt, FastScene can generate a 3D scene within a mere 15 minutes, which is at least one hour faster than state-of-the-art methods, making it a paradigm for user-friendly scene generation.

cs.CV↗

arXiv2024

MARE: Multi-Agents Collaboration Framework for Requirements Engineering

Requirements Engineering (RE) is a critical phase in the software development process that generates requirements specifications from stakeholders' needs. Recently, deep learning techniques have been successful in several RE tasks. However, obtaining high-quality requirements specifications requires collaboration across multiple tasks and roles. In this paper, we propose an innovative framework called MARE, which leverages collaboration among large language models (LLMs) throughout the entire RE process. MARE divides the RE process into four tasks: elicitation, modeling, verification, and specification. Each task is conducted by engaging one or two specific agents and each agent can conduct several actions. MARE has five agents and nine actions. To facilitate collaboration between agents, MARE has designed a workspace for agents to upload their generated intermediate requirements artifacts and obtain the information they need. We conduct experiments on five public cases, one dataset, and four new cases created by this work. We compared MARE with three baselines using three widely used metrics for the generated requirements models. Experimental results show that MARE can generate more correct requirements models and outperform the state-of-the-art approaches by 15.4%. For the generated requirements specifications, we conduct a human evaluation in three aspects and provide insights about the quality

cs.SE↗

arXiv2024

Latent Modulated Function for Computational Optimal Continuous Image Representation

The recent work Local Implicit Image Function (LIIF) and subsequent Implicit Neural Representation (INR) based works have achieved remarkable success in Arbitrary-Scale Super-Resolution (ASSR) by using MLP to decode Low-Resolution (LR) features. However, these continuous image representations typically implement decoding in High-Resolution (HR) High-Dimensional (HD) space, leading to a quadratic increase in computational cost and seriously hindering the practical applications of ASSR. To tackle this problem, we propose a novel Latent Modulated Function (LMF), which decouples the HR-HD decoding process into shared latent decoding in LR-HD space and independent rendering in HR Low-Dimensional (LD) space, thereby realizing the first computational optimal paradigm of continuous image representation. Specifically, LMF utilizes an HD MLP in latent space to generate latent modulations of each LR feature vector. This enables a modulated LD MLP in render space to quickly adapt to any input feature vector and perform rendering at arbitrary resolution. Furthermore, we leverage the positive correlation between modulation intensity and input image complexity to design a Controllable Multi-Scale Rendering (CMSR) algorithm, offering the flexibility to adjust the decoding efficiency based on the rendering precision. Extensive experiments demonstrate that converting existing INR-based ASSR methods to LMF can reduce the computational cost by up to 99.9%, accelerate inference by up to 57 times, and save up to 76% of parameters, while maintaining competitive performance. The code is available at https://github.com/HeZongyao/LMF.

cs.CV↗

arXiv2024

NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.

cs.CV↗

arXiv2024

EVIT: Event-Oriented Instruction Tuning for Event Reasoning

Events refer to specific occurrences, incidents, or happenings that take place under a particular background. Event reasoning aims to infer events according to certain relations and predict future events. The cutting-edge techniques for event reasoning play a crucial role in various natural language processing applications. Large language models (LLMs) have made significant advancements in event reasoning owing to their wealth of knowledge and reasoning capabilities. However, smaller instruction-tuned models currently in use do not consistently demonstrate exceptional proficiency in managing these tasks. This discrepancy arises from the absence of explicit modeling of events and the interconnections of them within their instruction data. Consequently, these models face challenges in comprehending event structures and semantics while struggling to bridge the gap between their interpretations and human understanding of events. Additionally, their limitations in grasping event relations lead to constrained event reasoning abilities to effectively deduce and incorporate pertinent event knowledge. In this paper, we propose Event-Oriented Instruction Tuning (EvIT) to train our LLM. Specifically, we first propose a novel structure named event quadruple which contains the structure and semantics of events and is complete in the event representation. We then design event-relation learning based on the structures. We encapsulate the learning into the instruction-tuning formulation to better stimulate the event reasoning capacity of our model. We design a heuristic unsupervised method to mine event quadruple from a large-scale corpus. At last, we finetune a Llama model on our Event-Oriented Instruction Tuning. We conduct extensive experiments on event reasoning tasks on several datasets. Automatic and human evaluations demonstrate EvIT achieves competitive performances on event reasoning.

cs.CL↗

arXiv2024

MEEL: Multi-Modal Event Evolution Learning

Multi-modal Event Reasoning (MMER) endeavors to endow machines with the ability to comprehend intricate event relations across diverse data modalities. MMER is fundamental and underlies a wide broad of applications. Despite extensive instruction fine-tuning, current multi-modal large language models still fall short in such ability. The disparity stems from that existing models are insufficient to capture underlying principles governing event evolution in various scenarios. In this paper, we introduce Multi-Modal Event Evolution Learning (MEEL) to enable the model to grasp the event evolution mechanism, yielding advanced MMER ability. Specifically, we commence with the design of event diversification to gather seed events from a rich spectrum of scenarios. Subsequently, we employ ChatGPT to generate evolving graphs for these seed events. We propose an instruction encapsulation process that formulates the evolving graphs into instruction-tuning data, aligning the comprehension of event reasoning to humans. Finally, we observe that models trained in this way are still struggling to fully comprehend event evolution. In such a case, we propose the guiding discrimination strategy, in which models are trained to discriminate the improper evolution direction. We collect and curate a benchmark M-EV2 for MMER. Extensive experiments on M-EV2 validate the effectiveness of our approach, showcasing competitive performance in open-source multi-modal LLMs.

cs.AI↗

arXiv2024

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories

How to evaluate Large Language Models (LLMs) in code generation is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. This paper proposes a new benchmark - EvoCodeBench to address the preceding problems, which has three primary advances. (1) EvoCodeBench aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) EvoCodeBench offers comprehensive annotations (e.g., requirements, reference code, and reference dependencies), and robust evaluation metrics (e.g., Pass@k and Recall@k). (3) EvoCodeBench is an evolving benchmark to avoid data leakage. We build an automatic pipeline to update EvoCodeBench from the latest repositories. We release the first version - EvoCodeBench-2403, containing 275 samples from 25 real-world repositories. Based on EvoCodeBench, we propose repository-level code generation and evaluate 10 popular LLMs (e.g., gpt-4, gpt-3.5, DeepSeek Coder, StarCoder 2, CodeLLaMa, Gemma, and Qwen 1.5). Our experiments reveal the coding abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 only is 20.73% in our experiments. We also analyze failed cases and summarize the shortcomings of existing LLMs in EvoCodeBench. We release EvoCodeBench, all prompts, and LLMs' completions for further community analysis.

cs.CL↗

arXiv2024

Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate programming challenges, thereby improving its performance in code generation. Nevertheless, smaller models have been struggling to keep up with LLMs in deducing these plans, adversely affecting their code generation capabilities. Given the considerable size and associated deployment costs, along with concerns about data security, many teams opt for deploying smaller models for code generation. Consequently, there arises a compelling need for transferring LLMs' code generation reasoning abilities to the smaller models. In this paper, we propose the CodePLAN framework, which aims to transfer LLMs' reasoning capabilities to smaller models through distillation. We adopt a multi-task learning approach, jointly undertaking code generation and solution plan generation tasks, to enhance the code generation capabilities of the smaller model. To ensure the superior quality of the solution plans, we advocate for the utilization of backward reasoning and plan sampling strategies. Our experiments show that in comparison to the conventional fine-tuning approach, our approach improves the smaller model's code generation performance (measured in pass@1 metric) by over 130% on the challenging APPS benchmark.

cs.SE↗

arXiv2024

DevEval: Evaluating Code Generation in Practical Software Projects

How to evaluate Large Language Models (LLMs) in code generation is an open question. Many benchmarks have been proposed but are inconsistent with practical software projects, e.g., unreal program distributions, insufficient dependencies, and small-scale project contexts. Thus, the capabilities of LLMs in practical projects are still unclear. In this paper, we propose a new benchmark named DevEval, aligned with Developers' experiences in practical projects. DevEval is collected through a rigorous pipeline, containing 2,690 samples from 119 practical projects and covering 10 domains. Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e.g., real program distributions, sufficient dependencies, and enough-scale project contexts. We assess five popular LLMs on DevEval (e.g., gpt-4, gpt-3.5-turbo, CodeLLaMa, and StarCoder) and reveal their actual abilities in code generation. For instance, the highest Pass@1 of gpt-3.5-turbo only is 42 in our experiments. We also discuss the challenges and future directions of code generation in practical projects. We open-source DevEval and hope it can facilitate the development of code generation in practical projects.

cs.SE↗

arXiv2024

IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been proposed to fine-tune LMs using supervised fine-tuning (SFT) techniques for code completion. However, the inherent exposure bias of these models can cause errors to accumulate early in the sequence completion, leading to even more errors in subsequent completions. To address this problem, deep reinforcement learning (DRL) is an alternative technique for fine-tuning LMs for code completion, which can improve the generalization capabilities and overall performance. Nevertheless, integrating DRL-based strategies into code completion faces two major challenges: 1) The dynamic nature of the code context requires the completion model to quickly adapt to changes, which poses difficulties for conventional DRL strategies that focus on delayed rewarding of the final code state. 2) It is difficult to evaluate the correctness of partial code, thus the reward redistribution-based strategies cannot be adapted to code completion. To tackle these challenges, we propose IRCoCo, a code completion-specific DRL-based fine-tuning framework. This framework is designed to provide immediate rewards as feedback for detecting dynamic context changes arising from continuous edits during code completion. With the aid of immediate feedback, the fine-tuned LM can gain a more precise understanding of the current context, thereby enabling effective adjustment of the LM and optimizing code completion in a more refined manner. Experimental results demonstrate that fine-tuning pretrained LMs with IRCoCo leads to significant improvements in the code completion task, outperforming both SFT-based and other DRL-based baselines.

cs.SE↗

arXiv2024

Knowledge-Aware Code Generation with Large Language Models

Large Language Models (LLMs) perform well on basic programming problems. However, they encounter challenges when dealing with complex tasks involving the use of diverse algorithmic and data structure skills, particularly programming competition-level problems. Notably, ChatGPT exhibits proficient performance on problems it has encountered during its pre-training phase, but this performance deteriorates when faced with novel problems. Consequently, enhancing the ability of LLMs to address unfamiliar problems has emerged as a pivotal research focus. The problem-solving process of LLMs mirrors human programmers' approach to a certain extent. When confronted with new programming tasks, human programmers engage in task planning and code writing with the previously acquired knowledge about algorithms and data structures. Despite having learned such knowledge, LLMs struggle to effectively apply it when faced with specific new problems. To address this issue, we constructed a novel dataset, CodeF, which contains a portion of programming problems that ChatGPT has not previously encountered. Furthermore, we developed a Knowledge Library tailored for Python programming contest problems and introduced the concept of Knowledge-Aware Code Generation (KareCoder). KareCoder bolsters the models' understanding and problem-solving capabilities by integrating prompt and knowledge from the library into the LLMs' code generation reasoning process, especially on Pass@1 metrics. Upon testing on the CodeF and APPS datasets, KareCoder demonstrated outstanding performance in handling novel problems previously unencountered by LLMs. In contrast with the code directly generated by ChatGPT, KareCoder achieved a relative improvement of 23.3% on the Pass@1 metric on the CodeF post2021-9 dataset. Additionally, it performs well compared to other methods when dealing with problems that LLMs have previously encountered.

cs.SE↗

arXiv2024

Incorporating Feature Signal Transmission with Block-based Haptic Data Reduction for Time-delayed Teleoperation

This paper presents an innovative feature signal transmission approach incorpo-rating block-based haptic data reduction to address time-delayed teleoperation. Numerous data reduction techniques rely on perceptual deadband (DB). In the preceding block-based approaches, the whole block within the DB is discarded. However, disregarding all signals within the DB loses too much information and hinders effective haptic signal tracking, as these signals contain valuable infor-mation for signal reconstruction. Consequently, we propose a feature signal transmission approach based on the block algorithm that aggregates samples as a unit, enabling high-quality haptic data reduction. In our proposed approach, we employ max-pooling to extract feature signals from the signals within the DB. These feature signals are then transmitted by adjusting the content of the trans-mission block. This methodology enables the transmission of more useful infor-mation without introducing additional delay, aside from the inherent algorithmic delay. Experimental results demonstrate the superiority of our approach over oth-er state-of-the-art (SOTA) methods on various assessment measures under dis-tinct channel delays.

cs.HC↗

arXiv2024

Exploring the Potential of Large Language Models in Self-adaptive Systems

Large Language Models (LLMs), with their abilities in knowledge acquisition and reasoning, can potentially enhance the various aspects of Self-adaptive Systems (SAS). Yet, the potential of LLMs in SAS remains largely unexplored and ambiguous, due to the lack of literature from flagship conferences or journals in the field, such as SEAMS and TAAS. The interdisciplinary nature of SAS suggests that drawing and integrating ideas from related fields, such as software engineering and autonomous agents, could unveil innovative research directions for LLMs within SAS. To this end, this paper reports the results of a literature review of studies in relevant fields, summarizes and classifies the studies relevant to SAS, and outlines their potential to specific aspects of SAS.

cs.SE↗