arXiv subjects

Pinjia He

Publications and source records attributed to Pinjia He.

At least 55 records · Page 3Linked to original sources

arXiv2024

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs

Multimodal Large Language Models (MLLMs) demonstrate a strong understanding of the real world and can even handle complex tasks. However, they still fail on some straightforward visual question-answering (VQA) problems. This paper dives deeper into this issue, revealing that models tend to err when answering easy questions (e.g. Yes/No questions) about an image, even though they can correctly describe it. We refer to this model behavior discrepancy between difficult and simple questions as model laziness. To systematically investigate model laziness, we manually construct LazyBench, a benchmark that includes Yes/No, multiple choice, short answer questions, and image description tasks that are related to the same subjects in the images. Based on LazyBench, we observe that laziness widely exists in current advanced MLLMs (e.g. GPT-4o, Gemini-1.5-pro, Claude 3 and LLaVA-v1.5-13B), and it is more pronounced on stronger models. We also analyze the VQA v2 (LLaVA-v1.5-13B) benchmark and find that about half of its failure cases are caused by model laziness, which further highlights the importance of ensuring that the model fully utilizes its capability. To this end, we conduct preliminary exploration on how to mitigate laziness and find that chain of thought (CoT) can effectively address this issue.

cs.CL↗

arXiv2024

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models

We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4. Despite LLMs' prowess in tasks like writing assistance, code generation, and machine translation, assessing their ability to reason has been challenging. Traditional evaluations often prioritize accuracy on downstream tasks over direct assessments of reasoning processes. LogicAsker addresses this gap by employing a set of atomic reasoning skills grounded in propositional and predicate logic to systematically examine and improve the reasoning prowess of LLMs. Our methodology reveals significant gaps in LLMs' learning of logical rules, with identified reasoning failures ranging from 29\% to 90\% across different models. Moreover, we leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5\%. To our knowledge, this is the first effort to utilize test case outcomes to effectively refine LLMs' formal reasoning capabilities. We make our code, data, and results publicly available (https://github.com/yxwan123/LogicAsker) to facilitate further research and replication of our findings.

cs.SE↗

arXiv2024

SPES: Towards Optimizing Performance-Resource Trade-Off for Serverless Functions

As an emerging cloud computing deployment paradigm, serverless computing is gaining traction due to its efficiency and ability to harness on-demand cloud resources. However, a significant hurdle remains in the form of the cold start problem, causing latency when launching new function instances from scratch. Existing solutions tend to use over-simplistic strategies for function pre-loading/unloading without full invocation pattern exploitation, rendering unsatisfactory optimization of the trade-off between cold start latency and resource waste. To bridge this gap, we propose SPES, the first differentiated scheduler for runtime cold start mitigation by optimizing serverless function provision. Our insight is that the common architecture of serverless systems prompts the concentration of certain invocation patterns, leading to predictable invocation behaviors. This allows us to categorize functions and pre-load/unload proper function instances with finer-grained strategies based on accurate invocation prediction. Experiments demonstrate the success of SPES in optimizing serverless function provision on both sides: reducing the 75th-percentile cold start rates by 49.77% and the wasted memory time by 56.43%, compared to the state-of-the-art. By mitigating the cold start issue, SPES is a promising advancement in facilitating cloud services deployed on serverless architectures.

cs.SE↗

arXiv2024

An Empirical Study on Package-Level Deprecation in Python Ecosystem

Open-source software (OSS) plays a crucial role in modern software development. Utilizing OSS code can greatly accelerate software development, reduce redundancy, and enhance reliability. Python, a widely adopted programming language, is renowned for its extensive and diverse third-party package ecosystem. However, a significant number of OSS packages within the Python ecosystem are in poor maintenance, leading to potential risks in functionality and security. Consequently, it is essential to establish a deprecation mechanism to assist package developers and users in managing packages effectively. To facilitate the establishment of the package-level deprecation mechanism, this paper presents a mixed-method empirical study, including data analysis and surveys. We investigate the current practices of announcing, receiving, and handling package-level deprecation in the Python ecosystem. We also assess the benefits of having deprecation announcements for inactively maintained packages. Furthermore, we investigate the challenges faced by package developers and users and their expectations for future deprecation practices. Our findings reveal that 75.4% of inactive package developers have no intention of releasing deprecation declarations for various reasons, while 89.5% of users express a desire to be notified about the deprecation, highlighting a gap between developers and users; in many cases, no alternative solutions are available when deprecation occurs, emphasizing the need to explore practical approaches that enable seamless package handover and require less maintenance effort. Our work aims to enhance the understanding of existing package-level deprecation patterns within the Python OSS realm and facilitate the development of deprecation practices for the Python community in the future.

cs.SE↗

arXiv2024

Unlocking the Power of Numbers: Log Compression via Numeric Token Parsing

Parser-based log compressors have been widely explored in recent years because the explosive growth of log volumes makes the compression performance of general-purpose compressors unsatisfactory. These parser-based compressors preprocess logs by grouping the logs based on the parsing result and then feed the preprocessed files into a general-purpose compressor. However, parser-based compressors have their limitations. First, the goals of parsing and compression are misaligned, so the inherent characteristics of logs were not fully utilized. In addition, the performance of parser-based compressors depends on the sample logs and thus it is very unstable. Moreover, parser-based compressors often incur a long processing time. To address these limitations, we propose Denum, a simple, general log compressor with high compression ratio and speed. The core insight is that a majority of the tokens in logs are numeric tokens (i.e. pure numbers, tokens with only numbers and special characters, and numeric variables) and effective compression of them is critical for log compression. Specifically, Denum contains a Numeric Token Parsing module, which extracts all numeric tokens and applies tailored processing methods (e.g. store the differences of incremental numbers like timestamps), and a String Processing module, which processes the remaining log content without numbers. The processed files of the two modules are then fed as input to a general-purpose compressor and it outputs the final compression results. Denum has been evaluated on 16 log datasets and it achieves an 8.7%-434.7% higher average compression ratio and 2.6x-37.7x faster average compression speed (i.e. 26.2MB/S) compared to the baselines. Moreover, integrating Denum's Numeric Token Parsing into existing log compressors can provide an 11.8% improvement in their average compression ratio and achieve 37% faster average compression speed.

cs.SE↗

arXiv2024

Exploring the Effectiveness of LLMs in Automated Logging Generation: An Empirical Study

Automated logging statement generation supports developers in documenting critical software runtime behavior. Given the great success in natural language generation and programming language comprehension, large language models (LLMs) might help developers generate logging statements, but this has not yet been investigated. To fill the gap, this paper performs the first study on exploring LLMs for logging statement generation.We first build a logging statement generation dataset, LogBench, with two parts: (1) LogBench-O: logging statements collected from GitHub repositories, and (2) LogBench-T: the transformed unseen code from LogBench-O. Then, we leverage LogBench to evaluate the effectiveness and generalization capabilities (using LogBench-T) of eleven top-performing LLMs. In addition, we examine the performance of these LLMs against classical retrieval-based and machine learning-based logging methods from the era preceding LLMs. We further evaluate LLM's logging generalization capabilities using unseen data (LogBench-T) derived from code transformation techniques. While existing LLMs deliver decent predictions on logging levels and logging variables, our study indicates that they only achieve a maximum BLEU score of 0.249, thus calling for improvements. The paper also highlights the importance of prompt constructions and external factors (e.g., programming contexts and code comments) for LLMs' logging performance. Based on these findings, we identify five implications and provide practical advice for future logging research. Our empirical analysis discloses the limitations of current logging approaches while showcasing the potential of LLM-based logging tools, and provides actionable guidance for building more practical models.

cs.SE↗

arXiv2024

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Safety lies at the core of the development of Large Language Models (LLMs). There is ample work on aligning LLMs with human ethics and preferences, including data filtering in pretraining, supervised fine-tuning, reinforcement learning from human feedback, and red teaming, etc. In this study, we discover that chat in cipher can bypass the safety alignment techniques of LLMs, which are mainly conducted in natural languages. We propose a novel framework CipherChat to systematically examine the generalizability of safety alignment to non-natural languages -- ciphers. CipherChat enables humans to chat with LLMs through cipher prompts topped with system role descriptions and few-shot enciphered demonstrations. We use CipherChat to assess state-of-the-art LLMs, including ChatGPT and GPT-4 for different representative human ciphers across 11 safety domains in both English and Chinese. Experimental results show that certain ciphers succeed almost 100% of the time to bypass the safety alignment of GPT-4 in several safety domains, demonstrating the necessity of developing safety alignment for non-natural languages. Notably, we identify that LLMs seem to have a ''secret cipher'', and propose a novel SelfCipher that uses only role play and several demonstrations in natural language to evoke this capability. SelfCipher surprisingly outperforms existing human ciphers in almost all cases. Our code and data will be released at https://github.com/RobustNLP/CipherChat.

cs.CL↗

arXiv2024

LILAC: Log Parsing using LLMs with Adaptive Parsing Cache

Log parsing transforms log messages into structured formats, serving as the prerequisite step for various log analysis tasks. Although a variety of log parsing approaches have been proposed, their performance on complicated log data remains compromised due to the use of human-crafted rules or learning-based models with limited training data. The recent emergence of powerful large language models (LLMs) demonstrates their vast pre-trained knowledge related to code and logging, making it promising to apply LLMs for log parsing. However, their lack of specialized log parsing capabilities currently hinders their accuracy in parsing. Moreover, the inherent inconsistent answers, as well as the substantial overhead, prevent the practical adoption of LLM-based log parsing. To address these challenges, we propose LILAC, the first practical log parsing framework using LLMs with adaptive parsing cache. To facilitate accurate and robust log parsing, LILAC leverages the in-context learning (ICL) capability of the LLM by performing a hierarchical candidate sampling algorithm and selecting high-quality demonstrations. Furthermore, LILAC incorporates a novel component, an adaptive parsing cache, to store and refine the templates generated by the LLM. It helps mitigate LLM's inefficiency issue by enabling rapid retrieval of previously processed log templates. In this process, LILAC adaptively updates the templates within the parsing cache to ensure the consistency of parsed results. The extensive evaluation on public large-scale datasets shows that LILAC outperforms state-of-the-art methods by 69.5% in terms of the average F1 score of template accuracy. In addition, LILAC reduces the query times to LLMs by several orders of magnitude, achieving a comparable efficiency to the fastest baseline.

cs.SE↗

arXiv2024

Prompting for Automatic Log Template Extraction

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance.

cs.SE↗

arXiv2024

Go Static: Contextualized Logging Statement Generation

Logging practices have been extensively investigated to assist developers in writing appropriate logging statements for documenting software behaviors. Although numerous automatic logging approaches have been proposed, their performance remains unsatisfactory due to the constraint of the single-method input, without informative programming context outside the method. Specifically, we identify three inherent limitations with single-method context: limited static scope of logging statements, inconsistent logging styles, and missing type information of logging variables. To tackle these limitations, we propose SCLogger, the first contextualized logging statement generation approach with inter-method static contexts. First, SCLogger extracts inter-method contexts with static analysis to construct the contextualized prompt for language models to generate a tentative logging statement. The contextualized prompt consists of an extended static scope and sampled similar methods, ordered by the chain-of-thought (COT) strategy. Second, SCLogger refines the access of logging variables by formulating a new refinement prompt for language models, which incorporates detailed type information of variables in the tentative logging statement. The evaluation results show that SCLogger surpasses the state-of-the-art approach by 8.7% in logging position accuracy, 32.1% in level accuracy, 19.6% in variable precision, and 138.4% in text BLEU-4 score. Furthermore, SCLogger consistently boosts the performance of logging statement generation across a range of large language models, thereby showcasing the generalizability of this approach.

cs.SE↗

arXiv2023

Retromorphic Testing: A New Approach to the Test Oracle Problem

A test oracle serves as a criterion or mechanism to assess the correspondence between software output and the anticipated behavior for a given input set. In automated testing, black-box techniques, known for their non-intrusive nature in test oracle construction, are widely used, including notable methodologies like differential testing and metamorphic testing. Inspired by the mathematical concept of inverse function, we present Retromorphic Testing, a novel black-box testing methodology. It leverages an auxiliary program in conjunction with the program under test, which establishes a dual-program structure consisting of a forward program and a backward program. The input data is first processed by the forward program and then its program output is reversed to its original input format using the backward program. In particular, the auxiliary program can operate as either the forward or backward program, leading to different testing modes. The process concludes by examining the relationship between the initial input and the transformed output within the input domain. For example, to test the implementation of the sine function $\sin(x)$, we can employ its inverse function, $\arcsin(x)$, and validate the equation $x = \sin(\arcsin(x)+2kπ), \forall k \in \mathbb{Z}$. In addition to the high-level concept of Retromorphic Testing, this paper presents its three testing modes with illustrative use cases across diverse programs, including algorithms, traditional software, and AI applications.

cs.SE↗

arXiv2023

Loghub: A Large Collection of System Log Datasets for AI-driven Log Analytics

Logs have been widely adopted in software system development and maintenance because of the rich runtime information they record. In recent years, the increase of software size and complexity leads to the rapid growth of the volume of logs. To handle these large volumes of logs efficiently and effectively, a line of research focuses on developing intelligent and automated log analysis techniques. However, only a few of these techniques have reached successful deployments in industry due to the lack of public log datasets and open benchmarking upon them. To fill this significant gap and facilitate more research on AI-driven log analytics, we have collected and released loghub, a large collection of system log datasets. In particular, loghub provides 19 real-world log datasets collected from a wide range of software systems, including distributed systems, supercomputers, operating systems, mobile systems, server applications, and standalone software. In this paper, we summarize the statistics of these datasets, introduce some practical usage scenarios of the loghub datasets, and present our benchmarking results on loghub to benefit the researchers and practitioners in this field. Up to the time of this paper writing, the loghub datasets have been downloaded for roughly 90,000 times in total by hundreds of organizations from both industry and academia. The loghub datasets are available at https://github.com/logpai/loghub.

cs.SE↗

arXiv2023

AutoLog: A Log Sequence Synthesis Framework for Anomaly Detection

The rapid progress of modern computing systems has led to a growing interest in informative run-time logs. Various log-based anomaly detection techniques have been proposed to ensure software reliability. However, their implementation in the industry has been limited due to the lack of high-quality public log resources as training datasets. While some log datasets are available for anomaly detection, they suffer from limitations in (1) comprehensiveness of log events; (2) scalability over diverse systems; and (3) flexibility of log utility. To address these limitations, we propose AutoLog, the first automated log generation methodology for anomaly detection. AutoLog uses program analysis to generate run-time log sequences without actually running the system. AutoLog starts with probing comprehensive logging statements associated with the call graphs of an application. Then, it constructs execution graphs for each method after pruning the call graphs to find log-related execution paths in a scalable manner. Finally, AutoLog propagates the anomaly label to each acquired execution path based on human knowledge. It generates flexible log sequences by walking along the log execution paths with controllable parameters. Experiments on 50 popular Java projects show that AutoLog acquires significantly more (9x-58x) log events than existing log datasets from the same system, and generates log messages much faster (15x) with a single machine than existing passive data collection approaches. We hope AutoLog can facilitate the benchmarking and adoption of automated log analysis techniques.

cs.SE↗

arXiv2023

An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software

The exponential growth of social media platforms has brought about a revolution in communication and content dissemination in human society. Nevertheless, these platforms are being increasingly misused to spread toxic content, including hate speech, malicious advertising, and pornography, leading to severe negative consequences such as harm to teenagers' mental health. Despite tremendous efforts in developing and deploying textual and image content moderation methods, malicious users can evade moderation by embedding texts into images, such as screenshots of the text, usually with some interference. We find that modern content moderation software's performance against such malicious inputs remains underexplored. In this work, we propose OASIS, a metamorphic testing framework for content moderation software. OASIS employs 21 transform rules summarized from our pilot study on 5,000 real-world toxic contents collected from 4 popular social media applications, including Twitter, Instagram, Sina Weibo, and Baidu Tieba. Given toxic textual contents, OASIS can generate image test cases, which preserve the toxicity yet are likely to bypass moderation. In the evaluation, we employ OASIS to test five commercial textual content moderation software from famous companies (i.e., Google Cloud, Microsoft Azure, Baidu Cloud, Alibaba Cloud and Tencent Cloud), as well as a state-of-the-art moderation research model. The results show that OASIS achieves up to 100% error finding rates. Moreover, through retraining the models with the test cases generated by OASIS, the robustness of the moderation model can be improved without performance degradation.

cs.SE↗

arXiv2023

Hue: A User-Adaptive Parser for Hybrid Logs

Log parsing, which extracts log templates from semi-structured logs and produces structured logs, is the first and the most critical step in automated log analysis. While existing log parsers have achieved decent results, they suffer from two major limitations by design. First, they do not natively support hybrid logs that consist of both single-line logs and multi-line logs (\eg Java Exception and Hadoop Counters). Second, they fall short in integrating domain knowledge in parsing, making it hard to identify ambiguous tokens in logs. This paper defines a new research problem, \textit{hybrid log parsing}, as a superset of traditional log parsing tasks, and proposes \textit{Hue}, the first attempt for hybrid log parsing via a user-adaptive manner. Specifically, Hue converts each log message to a sequence of special wildcards using a key casting table and determines the log types via line aggregating and pattern extracting. In addition, Hue can effectively utilize user feedback via a novel merge-reject strategy, making it possible to quickly adapt to complex and changing log templates. We evaluated Hue on three hybrid log datasets and sixteen widely-used single-line log datasets (\ie Loghub). The results show that Hue achieves an average grouping accuracy of 0.845 on hybrid logs, which largely outperforms the best results (0.563 on average) obtained by existing parsers. Hue also exhibits SOTA performance on single-line log datasets. Furthermore, Hue has been successfully deployed in a real production environment for daily hybrid log parsing.

cs.SE↗

arXiv2023

Automated Testing and Improvement of Named Entity Recognition Systems

Named entity recognition (NER) systems have seen rapid progress in recent years due to the development of deep neural networks. These systems are widely used in various natural language processing applications, such as information extraction, question answering, and sentiment analysis. However, the complexity and intractability of deep neural networks can make NER systems unreliable in certain circumstances, resulting in incorrect predictions. For example, NER systems may misidentify female names as chemicals or fail to recognize the names of minority groups, leading to user dissatisfaction. To tackle this problem, we introduce TIN, a novel, widely applicable approach for automatically testing and repairing various NER systems. The key idea for automated testing is that the NER predictions of the same named entities under similar contexts should be identical. The core idea for automated repairing is that similar named entities should have the same NER prediction under the same context. We use TIN to test two SOTA NER models and two commercial NER APIs, i.e., Azure NER and AWS NER. We manually verify 784 of the suspicious issues reported by TIN and find that 702 are erroneous issues, leading to high precision (85.0%-93.4%) across four categories of NER errors: omission, over-labeling, incorrect category, and range error. For automated repairing, TIN achieves a high error reduction rate (26.8%-50.6%) over the four systems under test, which successfully repairs 1,056 out of the 1,877 reported NER errors.

cs.CL↗

arXiv2023

ROME: Testing Image Captioning Systems via Recursive Object Melting

Image captioning (IC) systems aim to generate a text description of the salient objects in an image. In recent years, IC systems have been increasingly integrated into our daily lives, such as assistance for visually-impaired people and description generation in Microsoft Powerpoint. However, even the cutting-edge IC systems (e.g., Microsoft Azure Cognitive Services) and algorithms (e.g., OFA) could produce erroneous captions, leading to incorrect captioning of important objects, misunderstanding, and threats to personal safety. The existing testing approaches either fail to handle the complex form of IC system output (i.e., sentences in natural language) or generate unnatural images as test cases. To address these problems, we introduce Recursive Object MElting (Rome), a novel metamorphic testing approach for validating IC systems. Different from existing approaches that generate test cases by inserting objects, which easily make the generated images unnatural, Rome melts (i.e., remove and inpaint) objects. Rome assumes that the object set in the caption of an image includes the object set in the caption of a generated image after object melting. Given an image, Rome can recursively remove its objects to generate different pairs of images. We use Rome to test one widely-adopted image captioning API and four state-of-the-art (SOTA) algorithms. The results show that the test cases generated by Rome look much more natural than the SOTA IC testing approach and they achieve comparable naturalness to the original images. Meanwhile, by generating test pairs using 226 seed images, Rome reports a total of 9,121 erroneous issues with high precision (86.47%-92.17%). In addition, we further utilize the test cases generated by Rome to retrain the Oscar, which improves its performance across multiple evaluation metrics.

cs.SE↗

arXiv2023

Validating Multimedia Content Moderation Software via Semantic Fusion

The exponential growth of social media platforms, such as Facebook and TikTok, has revolutionized communication and content publication in human society. Users on these platforms can publish multimedia content that delivers information via the combination of text, audio, images, and video. Meanwhile, the multimedia content release facility has been increasingly exploited to propagate toxic content, such as hate speech, malicious advertisements, and pornography. To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content. However, due to the complexity of content moderation models and the difficulty of understanding information across multiple modalities, existing content moderation software can fail to detect toxic content, which often leads to extremely negative impacts. We introduce Semantic Fusion, a general, effective methodology for validating multimedia content moderation software. Our key idea is to fuse two or more existing single-modal inputs (e.g., a textual sentence and an image) into a new input that combines the semantics of its ancestors in a novel manner and has toxic nature by construction. This fused input is then used for validating multimedia content moderation software. We realized Semantic Fusion as DUO, a practical content moderation software testing tool. In our evaluation, we employ DUO to test five commercial content moderation software and two state-of-the-art models against three kinds of toxic content. The results show that DUO achieves up to 100% error finding rate (EFR) when testing moderation software. In addition, we leverage the test cases generated by DUO to retrain the two models we explored, which largely improves model robustness while maintaining the accuracy on the original test set.

cs.SE↗