Search

There are two classes of gamma-ray transients with a duration shorter than 2 seconds. One consists of cosmic short Gamma-Ray Bursts (GRBs) taking place in the deep universe via the neutron star mergers, and the other is the magnetar giant flares (GFs) with energies of $\sim 10^{44}-10^{46}$ erg from ``nearby" galaxies. Though the magnetar GFs and the short GRBs have rather similar temporal and spectral properties, their energies ($E_{\rm \gamma,iso}$) are different by quite a few orders of magnitude and hence can be distinguished supposing the host galaxies have been robustly identified. The newly observed GRB 231115A has been widely discussed as a new GF event for its high probability of being associated with M82. Here we conduct a detailed analysis of its prompt emission observed by Fermi-GBM, and compare the parameters with existing observations. The prompt gamma-ray radiation properties of GRB 231115A, if associated with M82, nicely follow the $E_{\rm p,z}-E_{\gamma,\rm iso}$ relation of the GFs, where $E_{\rm p,z}$ is the peak energy of the gamma-ray spectrum after the redshift ($z$) correction. To be a short GRB, the reshift needs to be $\sim 1$. Though such a chance is low, the available X-ray/GeV observation upper limits are not stringent enough to further rule out this possibility. We have also discussed the prospect of convincingly establishing the magnetar origin of GRB 231115A-like events in the future., Comment: 15 pages, 8 figures, 2 tables, accepted for publication in ApJ

The Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM, encompassing diverse skills related to understanding spatial relationships among objects and between objects and the scene area. Industries such as autonomous driving, smart healthcare, robotics, virtual, and augmented reality heavily demand MLLM's spatial awareness capabilities. However, there exists a noticeable gap between the current spatial awareness capabilities of MLLM and the requirements set by human needs. To address this issue, this paper proposes using more precise spatial position information between objects to guide MLLM in providing more accurate responses to user-related inquiries. Specifically, for a particular multi-modal task, we utilize algorithms for acquiring geometric spatial information and scene graphs to obtain relevant geometric spatial information and scene details of objects involved in the query. Subsequently, based on this information, we direct MLLM to address spatial awareness-related queries posed by the user. Extensive experiments were conducted in benchmarks such as MME, MM-Vet, and other multi-modal large language models. The experimental results thoroughly confirm the efficacy of the proposed method in enhancing the spatial awareness tasks and associated tasks of MLLM.

Large language models have shown good performances in generating code to meet human requirements. However, human requirements expressed in natural languages can be vague, incomplete, and ambiguous, leading large language models to misunderstand human requirements and make mistakes. Worse, it is difficult for a human user to refine the requirement. To help human users refine their requirements and improve large language models' code generation performances, we propose ChatCoder: a method to refine the requirements via chatting with large language models. We design a chat scheme in which the large language models will guide the human users to refine their expression of requirements to be more precise, unambiguous, and complete than before. Experiments show that ChatCoder has improved existing large language models' performance by a large margin. Besides, ChatCoder has the advantage over refine-based methods and LLMs fine-tuned via human response.

The long gamma-ray burst GRB 191221B has abundant observations in X-ray, optical and radio bands. In the literature, the observed optical light curve of GRB 191221B displays a plateau around 0.1-day, which is rather peculiar in gamma-ray bursts. Here we performed detailed analysis of the observational data from Swift/UVOT, VLT and LCO, obtained the light curve of the multi-band afterglow of GRB 191221B. By examining optical, ultraviolet, X-ray, and radio data for this event, we demonstrate that an on-axis two-component jet model can explain the observations. Our analysis suggests that the narrow component has an initial Lorentz factor of 400 and a jet opening half-angle of $1.4^{\circ}$, while the wide component has an initial Lorentz factor of 25 and a jet opening half-angle of $2.8^{\circ}$. The narrow jet dominates the early decay, whereas the wider jet causes the optical plateau and dominates late decay. According to this model, the reason for the absence of the X-ray plateau is due to the steeper spectral index of the wide component, resulting in a less significant flux contribution from the wide jet in the X-ray bands than in the optical bands. Moreover, we have explained the inconsistency in the decay indices of the UVOT and Rc-band data around 2000 seconds using reverse shock emission., Comment: 10 pages, 7 figures, Accepted by the Monthly Notices of the Royal Astronomical Society

Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. LLMs take a prompt consisting of requirement-code examples and a new requirement as input, and output new programs. Existing studies have found that ICL is highly dominated by the examples and thus arises research on example selection. However, existing approaches randomly select examples or only consider the textual similarity of requirements to retrieve, leading to sub-optimal performance. In this paper, we propose a novel learning-based selection approach named LAIL (LLM-Aware In-context Learning) for code generation. Given a candidate example, we exploit LLMs themselves to estimate it by considering the generation probabilities of ground-truth programs given a requirement and the example. We then label candidate examples as positive or negative through the probability feedback. Based on the labeled data, we import a contrastive learning objective to train an effective retriever that acquires the preference of LLMs in code generation. We apply LAIL to three LLMs and evaluate it on three representative datasets (e.g., MBJP, MBPP, and MBCPP). LATA outperforms the state-of-the-art baselines by 11.58%, 6.89%, and 5.07% on CodeGen, and 4.38%, 2.85%, and 2.74% on GPT-3.5 in terms of Pass@1, respectively.

We provide a generalized definition of polygamy relations for any quantum correlation measures. Instead of the usual polygamy inequality, a polygamy relation with equality is given by introducing the polygamy weight. From the polygamy relation with equality, we present polygamy inequalities satisfied by the $\beta$th $(\beta>0)$ power of the quantum correlation measures. Taking concurrence of assistance as an example, we further illustrate the significance and advantages of these relations. We also obtain a polygamy relation with equality by considering the one-to-group entanglements for any quantum entanglement measures that do not satisfy the polygamy relations. We demonstrate that such relations for tripartite states can be generalized to multipartite systems.

Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL). Due to this oversight, a better decoding strategy for code generation remains an open question. In this paper, we conduct the first systematic study to explore a decoding strategy specialized in code generation. With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred. Among them, the challenging tokens mainly appear at the beginning of a code block. Inspired by the above findings, we propose a simple yet effective method: Adaptive Temperature (AdapT) sampling, which dynamically adjusts the temperature coefficient when decoding different tokens. We apply a larger temperature when sampling for challenging tokens, allowing LLMs to explore diverse choices. We employ a smaller temperature for confident tokens avoiding the influence of tail randomness noises. We apply AdapT sampling to LLMs with different sizes and conduct evaluations on two popular datasets. Results show that AdapT sampling significantly outperforms state-of-the-art decoding strategy., Comment: This paper is accepted by AAAI 2024

Bug fixing holds significant importance in software development and maintenance. Recent research has made notable progress in exploring the potential of large language models (LLMs) for automatic bug fixing. However, existing studies often overlook the collaborative nature of bug resolution, treating it as a single-stage process. To overcome this limitation, we introduce a novel stage-wise framework named STEAM in this paper. The objective of STEAM is to simulate the interactive behavior of multiple programmers involved in various stages across the bug's life cycle. Taking inspiration from bug management practices, we decompose the bug fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to imitate the collaborative abilities of programmers during the resolution of software bugs. By harnessing the collective contribution, STEAM effectively enhances the bug-fixing capabilities of LLMs. We implement STEAM by employing the powerful dialogue-based LLM -- ChatGPT. Our evaluation on the widely adopted bug-fixing benchmark demonstrates that STEAM has achieved a new state-of-the-art level of bug-fixing performance., Comment: 13 pages, 8 figures

In recent years, Transformer networks are beginning to replace pure convolutional neural networks (CNNs) in the field of computer vision due to their global receptive field and adaptability to input. However, the quadratic computational complexity of softmax-attention limits the wide application in image dehazing task, especially for high-resolution images. To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity. A multi-scale attention refinement module is proposed as a complement to correct the error of the Taylor expansion. Furthermore, we introduce a multi-branch architecture with multi-scale patch embedding to the proposed Transformer, which embeds features by overlapping deformable convolution of different scales. The design of multi-scale patch embedding is based on three key ideas: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field. Our model, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), can embed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost. Experimental results on several dehazing benchmarks show that MB-TaylorFormer achieves state-of-the-art (SOTA) performance with a light computational burden. The source code and pre-trained models are available at https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer., Comment: ICCV 2023

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Code summarization aims to generate natural language descriptions automatically for source code. Code summaries are highly structured and have repetitive patterns. Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code. However, the state-of-the-art approaches perform poorly on predicting the keywords, which leads to the generated summaries suffering a loss in informativeness. To alleviate this problem, this paper proposes a novel retrieve-and-edit approach named EditSum for code summarization. Specifically, EditSum first retrieves a similar code snippet from a pre-defined corpus and treats its summary as a prototype summary to learn the pattern. Then, EditSum edits the prototype automatically to combine the pattern in the prototype with the semantic information of input code. Our motivation is that the retrieved prototype provides a good start-point for post-generation because the summaries of similar code snippets often have the same pattern. The post-editing process further reuses the patternized words in the prototype and generates keywords based on the semantic information of input code. We conduct experiments on a large-scale Java corpus and experimental results demonstrate that EditSum outperforms the state-of-the-art approaches by a substantial margin. The human evaluation also proves the summaries generated by EditSum are more informative and useful. We also verify that EditSum performs well on predicting the patternized words and keywords., Comment: Accepted by the 36th IEEE/ACM International Conference on Automated Software Engineering (ASE 2021)

Developers introduce code clones to improve programming productivity. Many existing studies have achieved impressive performance in monolingual code clone detection. However, during software development, more and more developers write semantically equivalent programs with different languages to support different platforms and help developers translate projects from one language to another. Considering that collecting cross-language parallel data, especially for low-resource languages, is expensive and time-consuming, how designing an effective cross-language model that does not rely on any parallel data is a significant problem. In this paper, we propose a novel method named ZC3 for Zero-shot Cross-language Code Clone detection. ZC3 designs the contrastive snippet prediction to form an isomorphic representation space among different programming languages. Based on this, ZC3 exploits domain-aware learning and cycle consistency learning to further constrain the model to generate representations that are aligned among different languages meanwhile are diacritical for different types of clones. To evaluate our approach, we conduct extensive experiments on four representative cross-language clone detection datasets. Experimental results show that ZC3 outperforms the state-of-the-art baselines by 67.12%, 51.39%, 14.85%, and 53.01% on the MAP score, respectively. We further investigate the representational distribution of different languages and discuss the effectiveness of our method., Comment: Accepted by the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)

For bright transients such as Gamma-Ray Bursts (GRBs), the Ultra-Violet/Optical Telescope (UVOT) operates under event mode at early phases, which records incident positions and arrival time for each photon. The event file is able to be screened into many exposures to study the early light curve of GRBs with a high time resolution, including in particular the rapid brightening of the UV/Optical emission. Such a goal, however, is hampered for some extremely bright GRBs by the saturation in UVOT event images. For moderately saturated UVOT sources, in this work we develop the method proposed in Jin et al. (2023) to recover their photometries. The basic idea is to assume a stable point spread function (PSF) of UVOT images, for which the counts in the core region (i.e., an aperture of a radius of 5 arcsec) and the wing region (i.e., an annulus ranging from 15 arcsec to 25 arcsec) should be a constant and the intrinsic flux can be reliably inferred with data in the ring. We demonstrate that in a given band, a tight correlation does hold among the background-removed count rates in the core and the wing. With the new method, the bright limit of measuring range for UVOT V and B bands increases ~ 1.7 mag, while only ~ 0.7 mag for U band due to the lack of bright calibration sources. Systematic uncertainties are ~ 0.2 mag for V, B and U bands., Comment: 27 pages, 19 figures, 3 tables, accepted to ApJS

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., Comment: Accepted to ACL

Recently, Fourier frequency information has attracted much attention in Low-Light Image Enhancement (LLIE). Some researchers noticed that, in the Fourier space, the lightness degradation mainly exists in the amplitude component and the rest exists in the phase component. By incorporating both the Fourier frequency and the spatial information, these researchers proposed remarkable solutions for LLIE. In this work, we further explore the positive correlation between the magnitude of amplitude and the magnitude of lightness, which can be effectively leveraged to improve the lightness of low-light images in the Fourier space. Moreover, we find that the Fourier transform can extract the global information of the image, and does not introduce massive neural network parameters like Multi-Layer Perceptrons (MLPs) or Transformer. To this end, a two-stage Fourier-based LLIE network (FourLLIE) is proposed. In the first stage, we improve the lightness of low-light images by estimating the amplitude transform map in the Fourier space. In the second stage, we introduce the Signal-to-Noise-Ratio (SNR) map to provide the prior for integrating the global Fourier frequency and the local spatial information, which recovers image details in the spatial space. With this ingenious design, FourLLIE outperforms the existing state-of-the-art (SOTA) LLIE methods on four representative datasets while maintaining good model efficiency.

Low-Light Image Enhancement (LLIE) aims to improve the perceptual quality of an image captured in low-light conditions. Generally, a low-light image can be divided into lightness and chrominance components. Recent advances in this area mainly focus on the refinement of the lightness, while ignoring the role of chrominance. It easily leads to chromatic aberration and, to some extent, limits the diverse applications of chrominance in customized LLIE. In this work, a ``brighten-and-colorize'' network (called BCNet), which introduces image colorization to LLIE, is proposed to address the above issues. BCNet can accomplish LLIE with accurate color and simultaneously enables customized enhancement with varying saturations and color styles based on user preferences. Specifically, BCNet regards LLIE as a multi-task learning problem: brightening and colorization. The brightening sub-task aligns with other conventional LLIE methods to get a well-lit lightness. The colorization sub-task is accomplished by regarding the chrominance of the low-light image as color guidance like the user-guide image colorization. Upon completion of model training, the color guidance (i.e., input low-light chrominance) can be simply manipulated by users to acquire customized results. This customized process is optional and, due to its decoupled nature, does not compromise the structural and detailed information of lightness. Extensive experiments on the commonly used LLIE datasets show that the proposed method achieves both State-Of-The-Art (SOTA) performance and user-friendly customization.

Quantifying genuine entanglement is a key task in quantum information theory. We study the quantification of genuine multipartite entanglement for four-qubit systems. Based on the concurrence of nine different classes of four-qubit states, with each class being closed under stochastic local operation and classical communication, we construct a concurrence tetrahedron. Proper genuine four-qubit entanglement measure is presented by using the volume of the concurrence tetrahedron. For non genuine entangled pure states, the four-qubit entanglement measure classifies the bi-separable entanglement. We show that the concurrence tetrahedron based measure of genuine four-qubit entanglement is not equivalent to the genuine four-partite entanglement concurrence. We illustrate the advantages of the concurrence tetrahedron by detailed examples., Comment: 23 pages, 4 figures

Decreased visibility, intensive noise, and biased color are the common problems existing in low-light images. These visual disturbances further reduce the performance of high-level vision tasks, such as object detection, and tracking. To address this issue, some image enhancement methods have been proposed to increase the image contrast. However, most of them are implemented only in the spatial domain, which can be severely influenced by noise signals while enhancing. Hence, in this work, we propose a novel residual recurrent multi-wavelet convolutional neural network R2-MWCNN learned in the frequency domain that can simultaneously increase the image contrast and reduce noise signals well. This end-to-end trainable network utilizes a multi-level discrete wavelet transform to divide input feature maps into distinct frequencies, resulting in a better denoise impact. A channel-wise loss function is proposed to correct the color distortion for more realistic results. Extensive experiments demonstrate that our proposed R2-MWCNN outperforms the state-of-the-art methods quantitively and qualitatively., Comment: 8 pages

Despite their ability to aid developers in detecting potential defects early in the software development life cycle, static analysis tools often suffer from precision issues (i.e., high false positive rates of reported alarms). To improve the availability of these tools, many automated warning identification techniques have been proposed to assist developers in classifying false positive alarms. However, existing approaches mainly focus on using hand-engineered features or statement-level abstract syntax tree token sequences to represent the defective code, failing to capture semantics from the reported alarms. To overcome the limitations of traditional approaches, this paper employs deep neural networks' powerful feature extraction and representation abilities to generate code semantics from control flow graph paths for warning identification. The control flow graph abstractly represents the execution process of a given program. Thus, the generated path sequences of the control flow graph can guide the deep neural networks to learn semantic information about the potential defect more accurately. In this paper, we fine-tune the pre-trained language model to encode the path sequences and capture the semantic representations for model building. Finally, this paper conducts extensive experiments on eight open-source projects to verify the effectiveness of the proposed approach by comparing it with the state-of-the-art baselines., Comment: 17 pages, in Chinese language, 9 figures

Recent years have witnessed the remarkable success of implicit neural representation methods. The recent work Local Implicit Image Function (LIIF) has achieved satisfactory performance for continuous image representation, where pixel values are inferred from a neural network in a continuous spatial domain. However, the computational cost of such implicit arbitrary-scale super-resolution (SR) methods increases rapidly as the scale factor increases, which makes arbitrary-scale SR time-consuming. In this paper, we propose Dynamic Implicit Image Function (DIIF), which is a fast and efficient method to represent images with arbitrary resolution. Instead of taking an image coordinate and the nearest 2D deep features as inputs to predict its pixel value, we propose a coordinate grouping and slicing strategy, which enables the neural network to perform decoding from coordinate slices to pixel value slices. We further propose a Coarse-to-Fine Multilayer Perceptron (C2F-MLP) to perform decoding with dynamic coordinate slicing, where the number of coordinates in each slice varies as the scale factor varies. With dynamic coordinate slicing, DIIF significantly reduces the computational cost when encountering arbitrary-scale SR. Experimental results demonstrate that DIIF can be integrated with implicit arbitrary-scale SR methods and achieves SOTA SR performance with significantly superior computational efficiency, thereby opening a path for real-time arbitrary-scale image representation. Our code can be found at https://github.com/HeZongyao/DIIF.

Quantifying coherence is an essential endeavor for both quantum mechanical foundations and quantum technologies. We present a bona fide measure of quantum coherence by utilizing the Tsallis relative operator $(\alpha, \beta)$-entropy. We first prove that the proposed coherence measure fulfills all the criteria of a well defined coherence measure, including the strong monotonicity in the resource theories of quantum coherence. We then study the ordering of the Tsallis relative operator $(\alpha, \beta)$-entropy of coherence, Tsallis relative $\alpha$-entropies of coherence, R\'{e}nyi $\alpha$-entropy of coherence and $l_{1}$ norm of coherence for both pure and mixed qubit states. This provides a new method for defining new coherence measure and entanglement measure, and also provides a new idea for further study of quantum coherence., Comment: 10 pages, 6 figures

Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to automate it. However, training bug localization model is usually challenging because it requires a large quantity of data labeled with the bug's exact location, which is difficult and time-consuming to collect. By contrast, obtaining bug detection data with binary labels of whether there is a bug in the source code is much simpler. This paper proposes a WEakly supervised bug LocaLization (WELL) method, which only uses the bug detection data with binary labels to train a bug localization model. With CodeBERT finetuned on the buggy-or-not binary labeled data, WELL can address bug localization in a weakly supervised manner. The evaluations on three method-level synthetic datasets and one file-level real-world dataset show that WELL is significantly better than the existing SOTA model in typical bug localization tasks such as variable misuse and other programming bugs., Comment: (Preprint) Software Engineer; Deep Learning; Bug Detection & Localization

Generating meaningful assert statements is one of the key challenges in automated test case generation, which requires understanding the intended functionality of the tested code. Recently, deep learning-based models have shown promise in improving the performance of assert statement generation. However, existing models only rely on the test prefixes along with their corresponding focal methods, yet ignore the developer-written summarization. Based on our observations, the summarization contents usually express the intended program behavior or contain parameters that will appear directly in the assert statement. Such information will help existing models address their current inability to accurately predict assert statements. This paper presents a novel summarization-guided approach for automatically generating assert statements. To derive generic representations for natural language (i.e., summarization) and programming language (i.e., test prefixes and focal methods), we leverage a pre-trained language model as the reference architecture and fine-tune it on the task of assert statement generation. To the best of our knowledge, the proposed approach makes the first attempt to leverage the summarization of focal methods as the guidance for making the generated assert statements more accurate. We demonstrate the effectiveness of our approach on two real-world datasets when compared with state-of-the-art models., Comment: Preprint, to appear in the Journal of Computer Science and Technology (JCST)

Events serve as fundamental units of occurrence within various contexts. The processing of event semantics in textual information forms the basis of numerous natural language processing (NLP) applications. Recent studies have begun leveraging large language models (LLMs) to address event semantic processing. However, the extent that LLMs can effectively tackle these challenges remains uncertain. Furthermore, the lack of a comprehensive evaluation framework for event semantic processing poses a significant challenge in evaluating these capabilities. In this paper, we propose an overarching framework for event semantic processing, encompassing understanding, reasoning, and prediction, along with their fine-grained aspects. To comprehensively evaluate the event semantic processing abilities of models, we introduce a novel benchmark called EVEVAL. We collect 8 datasets that cover all aspects of event semantic processing. Extensive experiments are conducted on EVEVAL, leading to several noteworthy findings based on the obtained results.

The patient-centered medical dialogue systems strive to offer diagnostic interpretation services to users who are less knowledgeable about medical knowledge, through emphasizing the importance of providing responses specific to the patients. It is difficult for the large language models (LLMs) to guarantee the specificity of responses in spite of its promising performance even in some tasks in medical field. Inspired by in-context learning, we propose PlugMed, a Plug-and-Play Medical Dialogue System, for addressing this challenge. PlugMed is equipped with two modules, the prompt generation (PG) module and the response ranking (RR) module, to enhances LLMs' dialogue strategies for improving the specificity of the dialogue. The PG module is designed to stimulate the imitative ability of LLMs by providing them with real dialogues from similar patients as prompts. The RR module incorporates fine-tuned small model as response filter to enable the selection of appropriate responses generated by LLMs. Furthermore, we introduce a new evaluation method based on matching both user's intent and high-frequency medical term to effectively assess the specificity of the responses. We conduct experimental evaluations on three medical dialogue datasets, and the results, including both automatic and human evaluation, demonstrate the effectiveness of our approach., Comment: Accepted by EMNLP 2023 Findings

Automated program repair is a crucial task for improving the efficiency of software developers. Recently, neural-based techniques have demonstrated significant promise in generating correct patches for buggy code snippets. However, most existing approaches arbitrarily treat the buggy context without any analysis to capture the semantic relationship between the buggy statement and its context. Additionally, we observe that existing neural models may output an unaltered patch consistent with the input buggy code snippet, which fails to be the correct human-written one for fixing the given bug. To address the aforementioned limitations, we present in this paper a novel neural program repair framework called \approach, which adapts the general pre-trained language model for fixing single-line Java bugs. We make the first attempt to use program slicing to extract contextual information directly related to the given buggy statement as repair ingredients from the corresponding program dependence graph and eliminate unaltered patches using an intuitive but effective filter mechanism. We demonstrate the effectiveness of \approach on five benchmarks when compared with state-of-the-art baselines., Comment: 12 pages, 7 figures

We study the monogamy of arbitrary quantum entanglement measures $E$ for tripartite quantum systems. Both sufficient and necessary conditions for $E$ to be monogamous in terms of the $\alpha$th power of $E$ are explicitly derived. It is shown that such monogamy of a entanglement measure $E$ only depends on the boundedness of the solution set of certain equations. Moreover, the monogamy conditions have been also obtained with respect to certain subsets of quantum states for a given quantum correlation. Detailed examples are given to illustrate our results., Comment: 6 pages, 2 figures

Large Language Models (LLMs) (e.g., ChatGPT) have shown impressive performance in code generation. LLMs take prompts as inputs, and Chain-of-Thought (CoT) prompting is the state-of-the-art prompting technique. CoT prompting asks LLMs first to generate CoTs (i.e., intermediate natural language reasoning steps) and then output the code. However, CoT prompting is designed for natural language generation and has low accuracy in code generation. In this paper, we propose Structured CoTs (SCoTs) and present a novel prompting technique for code generation, named SCoT prompting. Our motivation is source code contains rich structural information and any code can be composed of three program structures (i.e., sequence, branch, and loop structures). Intuitively, structured intermediate reasoning steps make for structured source code. Thus, we ask LLMs to use program structures to build CoTs, obtaining SCoTs. Then, LLMs generate the final code based on SCoTs. Compared to CoT prompting, SCoT prompting explicitly constrains LLMs to think about how to solve requirements from the view of source code and further the performance of LLMs in code generation. We apply SCoT prompting to two LLMs (i.e., ChatGPT and Codex) and evaluate it on three benchmarks (i.e., HumanEval, MBPP, and MBCPP). (1) SCoT prompting outperforms the state-of-the-art baseline - CoT prompting by up to 13.79% in Pass@1. (2) Human evaluation shows human developers prefer programs from SCoT prompting. (3) SCoT prompting is robust to examples and achieves substantial improvements., Comment: arXiv admin note: text overlap with arXiv:2303.17780

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task. We execute the generated code on the example test case provided in the question and wrap execution results into a supplementary comment. Utilizing this comment as guidance, our fault-aware code editor is employed to correct errors in the generated code. We perform extensive evaluations across two competitive programming datasets with nine different LLMs. Compared to directly generating from LLMs, our approach can improve the average of pass@1 by 89\% on APPS-dev, 31\% on APPS-test, and 48\% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. Compared to other post-processing methods, our method demonstrates superior accuracy and efficiency., Comment: Accepted by ACL2023

Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. These models may generate APIs that do not meet requirements or refer to non-existent APIs in third-party libraries, especially for lesser-known or private libraries. Inspired by the process of human developers using tools to search APIs, we propose ToolCoder, a novel approach that integrates API search tools with existing models to assist in code generation and API selection. To teach our model to use tools, we introduce an automated data annotation method using ChatGPT to add tool usage information into the source code data and fine-tune code generation models. During inference, we integrate API search tools into the generation process so that our model can automatically use the search tool to get suggestions when selecting an API. Our experimental results demonstrate that ToolCoder exhibits excellent performance and generalization across five public and private library code generation benchmarks, with at least 6.21\% improvement on average pass@1 metrics and 9.64\% improvement on average pass@10 metrics compared to state-of-the-art methods. Furthermore, we show that our relatively small ToolCoder model is comparable to one of the current best models, GPT-3.5, highlighting the potential of incorporating programming tools into the code generation process.

Studies have proposed that there is evidence for cosmological coupling of black holes (BHs) with an index of $k\approx 3$; hence, BHs serve as the astrophysical source of dark energy. However, the data sample is limited for the redshifts of $\leq 2.5$. In recent years, the James Webb Space Telescope (JWST) has detected many high-redshift active galactic nuclei (AGNs) and quasars. Among the JWST NIRSpec-/NIRCam-resolved AGNs, three are determined to be in early-type host galaxies with a redshift of $z\sim 4.5--7$. However, their $M_{\star}$ and $M_{\rm BH}$ are in tension with the predicted cosmological coupling of black holes with $k = 3$ at a confidence level of $\sim 2\sigma$, which challenges the hypothesis that BHs serve as the origin of dark energy. Future work on high-redshift AGNs using the JWST will further assess such a hypothesis by identifying more early-type host galaxies in the higher mass range., Comment: 9 pages, 3 figures, 2 tables; Comments are welcome!

Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a long time, a bottleneck for existing approaches is that given a code snippet, they can only generate one comment while developers usually need to know information from diverse perspectives such as what is the functionality of this code snippet and how to use it. To tackle this limitation, this study empirically investigates the feasibility of utilizing large language models (LLMs) to generate comments that can fulfill developers' diverse intents. Our intuition is based on the facts that (1) the code and its pairwise comment are used during the pre-training process of LLMs to build the semantic connection between the natural language and programming language, and (2) comments in the real-world projects, which are collected for the pre-training, usually contain different developers' intents. We thus postulate that the LLMs can already understand the code from different perspectives after the pre-training. Indeed, experiments on two large-scale datasets demonstrate the rationale of our insights: by adopting the in-context learning paradigm and giving adequate prompts to the LLM (e.g., providing it with ten or more examples), the LLM can significantly outperform a state-of-the-art supervised learning approach on generating comments with multiple intents. Results also show that customized strategies for constructing the prompts and post-processing strategies for reranking the results can both boost the LLM's performances, which shed light on future research directions for using LLMs to achieve comment generation., Comment: Accepted by the 46th International Conference on Software Engineering (ICSE 2024)

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., Comment: Accepted to TOSEM

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.

Source code representation with deep learning techniques is an important research field. There have been many studies that learn sequential or structural information for code representation. But sequence-based models and non-sequence-models both have their limitations. Researchers attempt to incorporate structural information to sequence-based models, but they only mine part of token-level hierarchical structure information. In this paper, we analyze how the complete hierarchical structure influences the tokens in code sequences and abstract this influence as a property of code tokens called hierarchical embedding. The hierarchical embedding is further divided into statement-level global hierarchy and token-level local hierarchy. Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model. We demonstrate the effectiveness of hierarchical embedding on learning code structure with an experiment on variable scope detection task. Further evaluation shows that HiT outperforms SOTA baseline models and show stable training efficiency on three source code-related tasks involving classification and generation tasks across 8 different datasets., Comment: Accepted by ICPC 2023

Although large language models (LLMs) have demonstrated impressive ability in code generation, they are still struggling to address the complicated intent provided by humans. It is widely acknowledged that humans typically employ planning to decompose complex problems and schedule solution steps prior to implementation. To this end, we introduce planning into code generation to help the model understand complex intent and reduce the difficulty of problem-solving. This paper proposes a self-planning code generation approach with large language models, which consists of two phases, namely planning phase and implementation phase. Specifically, in the planning phase, LLM plans out concise solution steps from the intent combined with few-shot prompting. Subsequently, in the implementation phase, the model generates code step by step, guided by the preceding solution steps. We conduct extensive experiments on various code-generation benchmarks across multiple programming languages. Experimental results show that self-planning code generation achieves a relative improvement of up to 25.4% in Pass@1 compared to direct code generation, and up to 11.9% compared to Chain-of-Thought of code generation. Moreover, our self-planning approach also enhances the quality of the generated code with respect to correctness, readability, and robustness, as assessed by humans., Comment: Accepted by TOSEM

Recently, deep learning techniques have shown great success in automatic code generation. Inspired by the code reuse, some researchers propose copy-based approaches that can copy the content from similar code snippets to obtain better performance. Practically, human developers recognize the content in the similar code that is relevant to their needs, which can be viewed as a code sketch. The sketch is further edited to the desired code. However, existing copy-based approaches ignore the code sketches and tend to repeat the similar code without necessary modifications, which leads to generating wrong results. In this paper, we propose a sketch-based code generation approach named SkCoder to mimic developers' code reuse behavior. Given a natural language requirement, SkCoder retrieves a similar code snippet, extracts relevant parts as a code sketch, and edits the sketch into the desired code. Our motivations are that the extracted sketch provides a well-formed pattern for telling models "how to write". The post-editing further adds requirement-specific details to the sketch and outputs the complete code. We conduct experiments on two public datasets and a new dataset collected by this work. We compare our approach to 20 baselines using 5 widely used metrics. Experimental results show that (1) SkCoder can generate more correct programs, and outperforms the state-of-the-art - CodeT5-base by 30.30%, 35.39%, and 29.62% on three datasets. (2) Our approach is effective to multiple code generation models and improves them by up to 120.1% in Pass@1. (3) We investigate three plausible code sketches and discuss the importance of sketches. (4) We manually evaluate the generated code and prove the superiority of our SkCoder in three aspects., Comment: Accepted by the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)

A proper code evaluation metric (CEM) profoundly impacts the evolution of code generation, which is an important research field in NLP and software engineering. Prevailing match-based CEMs (e.g., BLEU, Accuracy, and CodeBLEU) suffer from two significant drawbacks. 1. They primarily measure the surface differences between codes without considering their functional equivalence. However, functional equivalence is pivotal in evaluating the effectiveness of code generation, as different codes can perform identical operations. 2. They are predominantly designed for the Ref-only input format. However, code evaluation necessitates versatility in input formats. Aside from Ref-only, there are NL-only and Ref\&NL formats, which existing match-based CEMs cannot effectively accommodate. In this paper, we propose CodeScore, a large language model (LLM)-based CEM, which estimates the functional correctness of generated code on three input types. To acquire CodeScore, we present UniCE, a unified code generation learning framework, for LLMs to learn code execution (i.e., learning PassRatio and Executability of generated code) with unified input. Extensive experimental results on multiple code evaluation datasets demonstrate that CodeScore absolutely improves up to 58.87% correlation with functional correctness compared to other CEMs, achieves state-of-the-art performance, and effectively handles three input formats., Comment: Accepted to TOSEM

Adversarial examples are important to test and enhance the robustness of deep code models. As source code is discrete and has to strictly stick to complex grammar and semantics constraints, the adversarial example generation techniques in other domains are hardly applicable. Moreover, the adversarial example generation techniques specific to deep code models still suffer from unsatisfactory effectiveness due to the enormous ingredient search space. In this work, we propose a novel adversarial example generation technique (i.e., CODA) for testing deep code models. Its key idea is to use code differences between the target input (i.e., a given code snippet as the model input) and reference inputs (i.e., the inputs that have small code differences but different prediction results with the target input) to guide the generation of adversarial examples. It considers both structure differences and identifier differences to preserve the original semantics. Hence, the ingredient search space can be largely reduced as the one constituted by the two kinds of code differences, and thus the testing process can be improved by designing and guiding corresponding equivalent structure transformations and identifier renaming transformations. Our experiments on 15 deep code models demonstrate the effectiveness and efficiency of CODA, the naturalness of its generated examples, and its capability of enhancing model robustness after adversarial fine-tuning. For example, CODA reveals 88.05% and 72.51% more faults in models than the state-of-the-art techniques (i.e., CARROT and ALERT) on average, respectively., Comment: Accepted by ASE 2023