arXiv subjects

Zhou Yang

Publications and source records attributed to Zhou Yang.

At least 91 records · Page 5Linked to original sources

arXiv2024

Enhancing Empathetic Response Generation by Augmenting LLMs with Small-scale Empathetic Models

Empathetic response generation is increasingly significant in AI, necessitating nuanced emotional and cognitive understanding coupled with articulate response expression. Current large language models (LLMs) excel in response expression; however, they lack the ability to deeply understand emotional and cognitive nuances, particularly in pinpointing fine-grained emotions and their triggers. Conversely, small-scale empathetic models (SEMs) offer strength in fine-grained emotion detection and detailed emotion cause identification. To harness the complementary strengths of both LLMs and SEMs, we introduce a Hybrid Empathetic Framework (HEF). HEF regards SEMs as flexible plugins to improve LLM's nuanced emotional and cognitive understanding. Regarding emotional understanding, HEF implements a two-stage emotion prediction strategy, encouraging LLMs to prioritize primary emotions emphasized by SEMs, followed by other categories, substantially alleviates the difficulties for LLMs in fine-grained emotion detection. Regarding cognitive understanding, HEF employs an emotion cause perception strategy, prompting LLMs to focus on crucial emotion-eliciting words identified by SEMs, thus boosting LLMs' capabilities in identifying emotion causes. This collaborative approach enables LLMs to discern emotions more precisely and formulate empathetic responses. We validate HEF on the Empathetic-Dialogue dataset, and the findings indicate that our framework enhances the refined understanding of LLMs and their ability to convey empathetic responses.

cs.HC↗

arXiv2024

Tapestry of dualities in decohered quantum error correction codes

Quantum error correction (QEC) codes protect quantum information from errors due to decoherence. Many of them also serve as prototypical models for exotic topological quantum matters. Investigating the behavior of the QEC codes under decoherence sheds light on not only the codes' robustness against errors but also new out-of-equilibrium quantum phases driven by decoherence. The phase transitions, including the error threshold, of the decohered QEC codes can be probed by the systems' Rényi entropies $S_R$ with different Rényi indices $R$. In this paper, we study the general construction of the statistical models that characterize the Rényi entropies of QEC codes decohered by Pauli noise. We show that these statistical models can be organized into a "tapestry" woven by rich duality relations among them. For Calderbank-Shor-Steane (CSS) codes with bit-flip and phase-flip errors, we show that each Rényi entropy is captured by a pair of dual statistical models with randomness. For $R=2,3,\infty$, there are additional dualities that map between the two error types, relating the critical bit-flip and phase-flip error rates of the decoherence-induced phase transitions in the CSS codes. For CSS codes with an "$em$ symmetry" between the $X$-type and the $Z$-type stabilizers, the dualities with $R=2,3,\infty$ become self-dualities with super-universal self-dual error rates. These self-dualities strongly constrain the phase transitions of the code signaled by $S_{R=2,3,\infty}$. For general stabilizer codes decohered by generic Pauli noise, we also construct the statistical models that characterize the systems' entropies and obtain general duality relations between Pauli noise with different error rates.

cond-mat.str-el↗

arXiv2024

Unveiling Memorization in Code Models

The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lines of code from both open-source and private repositories. A code model memorizes and produces source code verbatim, which potentially contains vulnerabilities, sensitive information, or code with strict licenses, leading to potential security and privacy issues. This paper investigates an important problem: to what extent do code models memorize their training data? We conduct an empirical study to explore memorization in large pre-trained code models. Our study highlights that simply extracting 20,000 outputs (each having 512 tokens) from a code model can produce over 40,125 code snippets that are memorized from the training data. To provide a better understanding, we build a taxonomy of memorized contents with 3 categories and 14 subcategories. The results show that the prompts sent to the code models affect the distribution of memorized contents. We identify several key factors of memorization. Specifically, given the same architecture, larger models suffer more from memorization problems. A code model produces more memorization when it is allowed to generate longer outputs. We also find a strong positive correlation between the number of an output's occurrences in the training data and that in the generated outputs, which indicates that a potential way to reduce memorization is to remove duplicates in the training data. We then identify effective metrics that infer whether an output contains memorization accurately. We also make suggestions to deal with memorization.

cs.SE↗

arXiv2024

Greening Large Language Models of Code

Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerful models, there remain several scenarios where developers cannot take full advantage of them, stemming from factors such as restricted or unreliable internet access, institutional privacy policies that prohibit external transmission of code to third-party vendors, and more. Therefore, developing a compact, efficient, and yet energy-saving model for deployment on developers' devices becomes essential. To this aim, we propose Avatar, a novel approach that crafts a deployable model from a large language model of code by optimizing it in terms of model size, inference latency, energy consumption, and carbon footprint while maintaining a comparable level of effectiveness. The key idea of Avatar is to formulate the optimization of language models as a multi-objective configuration tuning problem and solve it with the help of a Satisfiability Modulo Theories (SMT) solver and a tailored optimization algorithm. The SMT solver is used to form an appropriate configuration space, while the optimization algorithm identifies the Pareto-optimal set of configurations for training the optimized models using knowledge distillation. We evaluate Avatar with two popular language models of code, i.e., CodeBERT and GraphCodeBERT, on two popular tasks, i.e., vulnerability prediction and clone detection. We use Avatar to produce optimized models with a small size (3 MB), which is 160$\times$ smaller than the original large models. On the two tasks, the optimized models significantly reduce the energy consumption (up to 184$\times$ less), carbon footprint (up to 157$\times$ less), and inference latency (up to 76$\times$ faster), with only a negligible loss in effectiveness (1.67\% on average).

cs.SE↗

arXiv2024

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from LeetCode. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.

cs.SE↗

arXiv2023

Source Code Data Augmentation for Deep Learning: A Survey

The increasingly popular adoption of deep learning models in many critical source code tasks motivates the development of data augmentation (DA) techniques to enhance training data and improve various capabilities (e.g., robustness and generalizability) of these models. Although a series of DA methods have been proposed and tailored for source code models, there lacks a comprehensive survey and examination to understand their effectiveness and implications. This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field. We start with an introduction of data augmentation in source code and then provide a discussion on major representative approaches. Next, we highlight the general strategies and techniques to optimize the DA quality. Subsequently, we underscore techniques useful in real-world source code scenarios and downstream tasks. Finally, we outline the prevailing challenges and potential opportunities for future research. In essence, we aim to demystify the corpus of existing literature on source code DA for deep learning, and foster further exploration in this sphere. Complementing this, we present a continually updated GitHub repository that hosts a list of update-to-date papers on DA for source code modeling, accessible at \url{https://github.com/terryyz/DataAug4Code}.

cs.CL↗

arXiv2023

Entanglement in one-dimensional critical state after measurements

The entanglement entropy (EE) of the ground state of a one-dimensional Hamiltonian at criticality has a universal logarithmic scaling with a prefactor given by the central charge $c$ of the underlying 1+1d conformal field theory. When the system is probed by measurements, the entanglement in the critical ground state is inevitably affected due to wavefunction collapse. In this paper, we study the effect of weak measurements on the entanglement scaling in the ground state of the one-dimensional critical transverse-field Ising model. For the measurements of the spins along their transverse spin axis, we identify interesting post-measurement states associated with spatially uniform measurement outcomes. The EE in these states still satisfies the logarithmic scaling but with an alternative prefactor given by the effective central charge $c_{\text{eff}}$. We derive the analytical expression of $c_{\text{eff}}$ as a function of the measurement strength. Using numerical simulations, we show that for the EE averaged over all post-measurement states based on their Born-rule probabilities, the numerically extracted effective central charge appears to be independent of the measurement strength, contrary to the usual expectation that local and non-overlapping measurements reduce the entanglement in the system. We also examine the behavior of the average EE under (biased) forced measurements where the measurement outcomes are sampled with a pre-determined probability distribution without inter-site correlations. In particular, we find an optimal probability distribution that can serve as a mean-field approximation to the Born-rule probabilities and lead to the same $c_{\text{eff}}$ behavior. The effects of the measurements along the longitudinal spin axis and the post-measurement correlation functions are also discussed.

quant-ph↗

arXiv2023

CCBERT: Self-Supervised Code Change Representation Learning

Numerous code changes are made by developers in their daily work, and a superior representation of code changes is desired for effective code change analysis. Recently, Hoang et al. proposed CC2Vec, a neural network-based approach that learns a distributed representation of code changes to capture the semantic intent of the changes. Despite demonstrated effectiveness in multiple tasks, CC2Vec has several limitations: 1) it considers only coarse-grained information about code changes, and 2) it relies on log messages rather than the self-contained content of the code changes. In this work, we propose CCBERT (\underline{C}ode \underline{C}hange \underline{BERT}), a new Transformer-based pre-trained model that learns a generic representation of code changes based on a large-scale dataset containing massive unlabeled code changes. CCBERT is pre-trained on four proposed self-supervised objectives that are specialized for learning code change representations based on the contents of code changes. CCBERT perceives fine-grained code changes at the token level by learning from the old and new versions of the content, along with the edit actions. Our experiments demonstrate that CCBERT significantly outperforms CC2Vec or the state-of-the-art approaches of the downstream tasks by 7.7\%--14.0\% in terms of different metrics and tasks. CCBERT consistently outperforms large pre-trained code models, such as CodeBERT, while requiring 6--10$\times$ less training time, 5--30$\times$ less inference time, and 7.9$\times$ less GPU memory.

cs.SE↗

arXiv2023

A Problem of Finite-Horizon Optimal Switching and Stochastic Control for Utility Maximization

In this paper, we undertake an investigation into the utility maximization problem faced by an economic agent who possesses the option to switch jobs, within a scenario featuring the presence of a mandatory retirement date. The agent needs to consider not only optimal consumption and investment but also the decision regarding optimal job-switching. Therefore, the utility maximization encompasses features of both optimal switching and stochastic control within a finite horizon. To address this challenge, we employ a dual-martingale approach to derive the dual problem defined as a finite-horizon pure optimal switching problem. By applying a theory of the double obstacle problem with non-standard arguments, we examine the analytical properties of the system of parabolic variational inequalities arising from the optimal switching problem, including those of its two free boundaries. Based on these analytical properties, we establish a duality theorem and characterize the optimal job-switching strategy in terms of time-varying wealth boundaries. Furthermore, we derive integral equation representations satisfied by the optimal strategies and provide numerical results based on these representations.

math.OC↗

arXiv2023

Stealthy Backdoor Attack for Code Models

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to backdoor attacks. A code model that is backdoor-attacked can behave normally on clean examples but will produce pre-defined malicious outputs on examples injected with triggers that activate the backdoors. Existing backdoor attacks on code models use unstealthy and easy-to-detect triggers. This paper aims to investigate the vulnerability of code models with stealthy backdoor attacks. To this end, we propose AFRAIDOOR (Adversarial Feature as Adaptive Backdoor). AFRAIDOOR achieves stealthiness by leveraging adversarial perturbations to inject adaptive triggers into different inputs. We evaluate AFRAIDOOR on three widely adopted code models (CodeBERT, PLBART and CodeT5) and two downstream tasks (code summarization and method name prediction). We find that around 85% of adaptive triggers in AFRAIDOOR bypass the detection in the defense process. By contrast, only less than 12% of the triggers from previous work bypass the defense. When the defense method is not applied, both AFRAIDOOR and baselines have almost perfect attack success rates. However, once a defense is applied, the success rates of baselines decrease dramatically to 10.47% and 12.06%, while the success rate of AFRAIDOOR are 77.05% and 92.98% on the two tasks. Our finding exposes security weaknesses in code models under stealthy backdoor attacks and shows that the state-of-the-art defense method cannot provide sufficient protection. We call for more research efforts in understanding security threats to code models and developing more effective countermeasures.

cs.CR↗

arXiv2023

Synthesizing Speech Test Cases with Text-to-Speech? An Empirical Study on the False Alarms in Automated Speech Recognition Testing

Recent studies have proposed the use of Text-To-Speech (TTS) systems to automatically synthesise speech test cases on a scale and uncover a large number of failures in ASR systems. However, the failures uncovered by synthetic test cases may not reflect the actual performance of an ASR system when it transcribes human audio, which we refer to as false alarms. Given a failed test case synthesised from TTS systems, which consists of TTS-generated audio and the corresponding ground truth text, we feed the human audio stating the same text to an ASR system. If human audio can be correctly transcribed, an instance of a false alarm is detected. In this study, we investigate false alarm occurrences in five popular ASR systems using synthetic audio generated from four TTS systems and human audio obtained from two commonly used datasets. Our results show that the least number of false alarms is identified when testing Deepspeech, and the number of false alarms is the highest when testing Wav2vec2. On average, false alarm rates range from 21% to 34% in all five ASR systems. Among the TTS systems used, Google TTS produces the least number of false alarms (17%), and Espeak TTS produces the highest number of false alarms (32%) among the four TTS systems. Additionally, we build a false alarm estimator that flags potential false alarms, which achieves promising results: a precision of 98.3%, a recall of 96.4%, an accuracy of 98.5%, and an F1 score of 97.3%. Our study provides insight into the appropriate selection of TTS systems to generate high-quality speech to test ASR systems. Additionally, a false alarm estimator can be a way to minimise the impact of false alarms and help developers choose suitable test inputs when evaluating ASR systems. The source code used in this paper is publicly available on GitHub at https://github.com/julianyonghao/FAinASRtest.

cs.SE↗

arXiv2023

BrickPal: Augmented Reality-based Assembly Instructions for Brick Models

The assembly instruction is a mandatory component of Lego-like brick sets.The conventional production of assembly instructions requires a considerable amount of manual fine-tuning, which is intractable for casual users and customized brick sets.Moreover, the traditional paper-based instructions lack expressiveness and interactivity.To tackle the two problems above, we present BrickPal, an augmented reality-based system, which visualizes assembly instructions in an augmented reality head-mounted display. It utilizes Natural Language Processing (NLP) techniques to generate plausible assembly sequences, and provide real-time guidance in the AR headset.Our user study demonstrates BrickPal's effectiveness at assisting users in brick assembly compared to traditional assembly methods. Additionally, the NLP algorithm-generated assembly sequences achieve the same usability with manually adapted sequences.

cs.HC↗

arXiv2023

APISENS- Sentiment Scoring Tool for APIs with Crowd-Knowledge

Utilizing pre-existing software artifacts, such as libraries and Application Programming Interfaces (APIs), is crucial for software development efficiency. However, the abundance of artifacts that provide similar functionality can lead to confusion among developers, resulting in a challenge for proper selection and implementation. Through our preliminary investigation, we found that utilizing the collective knowledge of a crowd can greatly assist developers in acquiring a thorough and complete understanding of the complexities involved in the software development process. Especially as emotions are an inseparable part of human nature, it influences developers' activities. In this regard, we attempt to build a tool that can retrieve sentiment information for software APIs so that developers can determine APIs to utilize for their tasks. We employ the dataset from the most popular platforms (i.e., Twitter and YouTube) to build our research prototype. The source code, tool, and demo video are available on GitHub at \url{https://github.com/FalconLK/APISens}.

cs.SE↗

arXiv2023

APIHarvest: Harvesting API Information from Various Online Sources

Using APIs to develop software applications is the norm. APIs help developers to build applications faster as they do not need to reinvent the wheel. It is therefore important for developers to understand the APIs that they plan to use. Developers should also make themselves aware of relevant information updates about APIs. In order to do so, developers need to find and keep track of relevant information about the APIs that they are concerned with. Yet, the API information is scattered across various online sources, which makes it difficult to track by hand. Moreover, identifying content that is related to an API is not trivial. Motivated by these challenges, in this work, we introduce a tool named \tool that aims to ease the process of finding API information from various online sources. \tool is built on works that link APIs or libraries to various online sources. It supports finding API information on GitHub repositories, Stack Overflow's posts, tweets, YouTube videos, and common vulnerability and exposure (CVE) entries; and is extensible to support other sources.

cs.SE↗

arXiv2023

What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues

Artificial Intelligence systems, which benefit from the availability of large-scale datasets and increasing computational power, have become effective solutions to various critical tasks, such as natural language understanding, speech recognition, and image processing. The advancement of these AI systems is inseparable from open-source software (OSS). This paper presents an empirical study that investigates the issues in the repositories of open-source AI repositories to assist developers in understanding problems during the process of employing AI systems. We collect 576 repositories from the PapersWithCode platform. Among these repositories, we find 24,953 issues by utilizing GitHub REST APIs. Our empirical study includes three phases. First, we manually analyze these issues to categorize the problems that developers are likely to encounter in open-source AI repositories. Specifically, we provide a taxonomy of 13 categories related to AI systems. The two most common issues are runtime errors (23.18%) and unclear instructions (19.53%). Second, we see that 67.5% of issues are closed. We also find that half of these issues resolve within four days. Moreover, issue management features, e.g., label and assign, are not widely adopted in open-source AI repositories. In particular, only 7.81% and 5.9% of repositories label issues and assign these issues to assignees, respectively. Finally, we empirically show that employing GitHub issue management features and writing issues with detailed descriptions facilitate the resolution of issues. Based on our findings, we make recommendations for developers to help better manage the issues of open-source AI repositories and improve their quality.

cs.SE↗

arXiv2023

NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python

Machine learning (ML) has gained much attention and been incorporated into our daily lives. While there are numerous publicly available ML projects on open source platforms such as GitHub, there have been limited attempts in filtering those projects to curate ML projects of high quality. The limited availability of such a high-quality dataset poses an obstacle in understanding ML projects. To help clear this obstacle, we present NICHE, a manually labelled dataset consisting of 572 ML projects. Based on evidences of good software engineering practices, we label 441 of these projects as engineered and 131 as non-engineered. This dataset can help researchers understand the practices that are followed in high-quality ML projects. It can also be used as a benchmark for classifiers designed to identify engineered ML projects.

cs.SE↗

arXiv2023

ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems

Recent years have witnessed wider adoption of Automated Speech Recognition (ASR) techniques in various domains. Consequently, evaluating and enhancing the quality of ASR systems is of great importance. This paper proposes ASDF, an Automated Speech Recognition Differential Testing Framework for testing ASR systems. ASDF extends an existing ASR testing tool, the CrossASR++, which synthesizes test cases from a text corpus. However, CrossASR++ fails to make use of the text corpus efficiently and provides limited information on how the failed test cases can improve ASR systems. To address these limitations, our tool incorporates two novel features: (1) a text transformation module to boost the number of generated test cases and uncover more errors in ASR systems and (2) a phonetic analysis module to identify on which phonemes the ASR system tend to produce errors. ASDF generates more high-quality test cases by applying various text transformation methods (e.g., change tense) to the texts in failed test cases. By doing so, ASDF can utilize a small text corpus to generate a large number of audio test cases, something which CrossASR++ is not capable of. In addition, ASDF implements more metrics to evaluate the performance of ASR systems from multiple perspectives. ASDF performs phonetic analysis on the identified failed test cases to identify the phonemes that ASR systems tend to transcribe incorrectly, providing useful information for developers to improve ASR systems. The demonstration video of our tool is made online at https://www.youtube.com/watch?v=DzVwfc3h9As. The implementation is available at https://github.com/danielyuenhx/asdf-differential-testing.

eess.AS↗

arXiv2023

Prioritizing Speech Test Cases

With the wide adoption of automated speech recognition (ASR) systems, it is increasingly important to test and improve ASR systems. However, collecting and executing speech test cases is usually expensive and time-consuming, motivating us to strategically prioritize speech test cases. A key question is: how to determine the ideal order of collecting and executing speech test cases to uncover more errors as early as possible? Each speech test case consists of a piece of audio and the corresponding reference text. In this work, we propose PROPHET (PRiOritizing sPeecH tEsT), a tool that predicts potential error-uncovering speech test cases only based on their reference texts. Thus, PROPHET analyzes test cases and prioritizes them without running the ASR system, which can analyze speech test cases at a large scale. We evaluate 6 different prioritization methods on 3 ASR systems and 12 datasets. Given the same testing budget, we find that our approach uncovers 12.63% more wrongly recognized words than the state-of-the-art method. We select test cases from the prioritized list to fine-tune ASR systems and analyze how our approach can improve the ASR system performance. Statistical tests show that our proposed method can bring significantly larger performance improvement to ASR systems than the existing baseline methods. Furthermore, we perform correlation analysis and confirm that fine-tuning an ASR system using a dataset, on which the model performs worse, tends to improve the performance more.

cs.SE↗