arXiv subjects

Xiaoning Du

Publications and source records attributed to Xiaoning Du.

At least 19 recordsLinked to original sources

arXiv2026

Detecting Incorrect LLM Explanations for Automated Program Repair

LLM-generated explanations help developers understand automated program repair (APR) rationale and assess patch quality. Incorrect explanations can mislead developers about a repair's reliability, making their detection important. However, manually inspecting the growing volume of generated repairs is impractical, motivating automated detection. Existing methods mainly target incorrect answers from general question-answering LLMs, often by sampling multiple responses and detecting contradictions. Applied to APR, they face two limitations: (1) they may depend on external verifiers that are unavailable or lack APR-specific reasoning; and (2) sampling strategies such as paraphrasing or re-prompting the same input often yield superficial, redundant responses that repeat the original error rather than expose it. We propose MetaReJ, the first method designed to detect incorrect APR explanations using metamorphic testing. Inspired by debate and viva examinations, MetaReJ challenges explanations through an argumentative strategy without requiring external verifiers. It applies novel metamorphic relations (MRs) to recursively question the LLM under equivalent and non-equivalent repair scenarios and detect contradictions. To obtain diverse samples, MetaReJ transforms the buggy program into variants that preserve or alter the underlying bug, then asks the LLM how to repair each variant. Contradictions among responses are encoded as MR violations, which indicate that the original explanation is incorrect. We evaluate MetaReJ on a manually labelled dataset of 1,756 explanations from multiple LLM-based APR systems. MetaReJ achieves an MCC of up to 0.43, outperforming prior methods by up to 333.3% in MCC.

cs.SE↗

arXiv2026

Talking to Itself While Coding: What Makes Comments Help Code Generation?

Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to generate the code that follows. However, it remains unclear which properties of comments affect code-generation performance. We study this question through observational analyses and controlled interventions. On LiveCodeBench, neither comment frequency nor broad comment intent reliably predicts pass@1. We then prefill weaker recipient models with comment blocks written by stronger source models, allowing us to separate comment surface form from the solution content they convey. Comments from source solutions that pass the tests raise recipient pass@1 by 17.2% on average. In contrast, comments describing failed solutions provide no reliable gain, while comments written for a different problem reduce pass@1 by 20.8%. Finally, across a wide range of models and prompt variants, most recipient models show no significant recovery of the external-comment gain, and the best case recovers only 24%. These results show that comments help code generation not merely because they are comments, but because they can provide correct solution content that prompting cannot reliably elicit.

cs.SE↗

arXiv2026

Extending Fill-In-the-Middle with Instructions for Steerable Code Completion

Code completion models often fail when the developer's intent is under-specified in the code context. To mitigate this, developers frequently use natural language comments to clarify objectives. However, current code completion models fail to prioritize these directives effectively since they are merely pre-trained using the Fill-In-the-Middle (FIM) objective. On the one hand, the natural language instructions, mixed with the noisy code comments, are just treated as part of the background context within the prefix. On the other hand, the pre-training datasets for the FIM objective are mostly sourced from open-source repositories, which results in a scarcity of high-intent instruction-to-code pairings that reflect the developers' workflow in code completion. To bridge this gap, we propose Instruction-aware Fill-In-the-Middle (IFIM), a fine-tuning method that extends the FIM structure with a dedicated, structurally separated instruction section. Our evaluation shows that IFIM substantially improves adherence to developer intent, while leaving infilling performance unchanged when no instruction is given. The gains hold on an in-the-wild benchmark of 100 instructions written by real developers and across model scales from 1.5B to 7B. IFIM thus offers a backward-compatible upgrade path for existing FIM-based code completion systems at a modest training cost.

cs.SE↗

arXiv2026

UntrustVul: An Automated Approach for Identifying Untrustworthy Alerts in Vulnerability Detection Models

Machine learning (ML) has shown promise in vulnerability detection, but ML detectors may rely on irrelevant code features, causing them to highlight non-vulnerable lines as suspicious. Such misleading predictions increase developers' manual effort and may lead to incorrect patching strategies, motivating the need to identify untrustworthy predictions automatically. We present UntrustVul, an approach for detecting untrustworthy vulnerability predictions by identifying suspicious lines that are inherently unrelated to vulnerabilities. UntrustVul leverages patterns from historical vulnerable lines and flags predictions as untrustworthy when the highlighted lines neither match known vulnerability patterns nor influence lines that do. A line is considered vulnerability-irrelevant if it does not resemble historical vulnerabilities and all its successors in the data and control dependency graph are also vulnerability-irrelevant. The approach is designed conservatively to minimise misclassifying trustworthy predictions as untrustworthy. We evaluate UntrustVul on 115K predictions from four models across the BigVul, MegaVul, SARD, and PrimeVul datasets. Results show that UntrustVul achieves AUC scores of 70%-88% and F1-scores of 82%-94%, outperforming existing approaches by 6%-59% in AUC and 13%-92% in F1-score.

cs.SE↗

arXiv2026

Towards Agentic Runtime Healing

Self-healing systems have long been a focus of research, aiming to enable software to recover from unexpected runtime errors without human intervention. Traditional approaches rely on predefined heuristic rules, such as reusing error handlers or rolling back to checkpoints, but these methods struggle to adapt to the diverse range of runtime errors. The emergence of Large Language Models offers a new opportunity to address this challenge. Leveraging their ability to understand and generate code and natural language, we propose using LLMs to dynamically generate error-handling strategies in real time, tailored to specific runtime contexts such as error messages and program states. We demonstrate the feasibility of this approach by designing such a framework, Healer, and empirically showing that it can handle runtime errors with a high success rate. When an unanticipated runtime error occurs, Healer leverages its internal LLM to generate bespoke error-handling code. The generated healing code is then executed to produce a corrected program state, allowing the program to continue execution with minimal disruption. We evaluate Healer across four code datasets and three state-of-the-art LLMs (GPT-3.5, GPT-4, and CodeQwen-7B), where GPT-4 can successfully recover from 72.8% of runtime errors, underscoring the promise of LLMs in this domain. Despite these promising results, challenges remain, particularly regarding the trustworthiness of LLM-generated code and its integration into existing systems. We mention potential solutions, such as safety checks and Healer-aware programming, to mitigate risks and ensure reliable operation. This work represents the first step toward agentic runtime healing, paving the way for more adaptive, resilient, and self-healing software systems.

cs.SE↗

arXiv2026

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking

Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and effectiveness in natural language generation. However, KGW's effectiveness degrades significantly under low-entropy settings such as code generation and mathematical reasoning. A crucial step in the KGW method is random vocabulary partitioning, which enables adjustments to token selection based on specific preferences. Our study revealed that the next-token probability distribution plays an critical role in determining how much, or even whether, we can modify token selection and, consequently, the effectiveness of watermarking. We refer to this characteristic, associated with the probability distribution of each token prediction, as \emph{watermark strength.} In cases of random vocabulary partitioning, the lower bound of watermark strength is dictated by the next-token probability distribution. However, we found that, by redesigning the vocabulary partitioning algorithm, we can potentially raise this lower bound. In this paper, we propose SSG (\textbf{S}ort-then-\textbf{S}plit by \textbf{G}roups), a method that partitions the vocabulary into two logit-balanced subsets. This design lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. Experiments on code generation and mathematical reasoning datasets demonstrate the effectiveness of SSG.

cs.CR↗

arXiv2025

Identifying and Mitigating API Misuse in Large Language Models

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development, as although LLMs demonstrate impressive code generation capabilities, their interactions with complex library APIs are often error-prone and can lead to software failures and vulnerabilities. In this paper, we conduct a large-scale study of API misuse patterns in LLM-generated code by analyzing both method selection and parameter usage across Python and Java, using three representative LLMs: StarCoder-7B, Qwen2.5-Coder-7B, and GitHub Copilot. Based on extensive manual annotation of 3,209 method-level and 3,492 parameter-level misuses, we identify and categorize four recurring misuse types by building on and refining prior API misuse taxonomies. Our evaluation of the three LLMs reveals persistent challenges in API usage, particularly hallucination and intent misalignment. To address these issues, we propose Dr.Fix, an LLM-based automatic repair approach guided by our taxonomy, which improves repair accuracy compared to baseline prompting and existing repair methods, achieving gains of up to 38.4 BLEU and 40% exact match on benchmark datasets. This work offers important insights into the current limitations of LLMs in API usage and points to directions for improving automated misuse repair in code generation systems.

cs.SE↗

arXiv2025

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE↗

arXiv2025

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand

Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One important factor is the inherent verbosity of programming languages, such as unnecessary formatting elements and lengthy boilerplate code. This leads to inflated token counts in both input and generated outputs, which increases inference costs and slows down the generation process. Prior work improves this through simplifying programming language grammar, reducing token usage across both code understanding and generation tasks. However, it is confined to syntactic transformations, leaving significant opportunities for token reduction unrealized at the semantic level. In this work, we propose Token Sugar, a concept that replaces frequent and verbose code patterns with reversible, token-efficient shorthand in the source code. To realize this concept in practice, we designed a systematic solution that mines high-frequency, token-heavy patterns from a code corpus, maps each to a unique shorthand, and integrates them into LLM pretraining via code transformation. With this solution, we obtain 799 (code pattern, shorthand) pairs, which can reduce up to 15.1% token count in the source code and is complementary to existing syntax-focused methods. We further trained three widely used LLMs on Token Sugar-augmented data. Experimental results show that these models not only achieve significant token savings (up to 11.2% reduction) during generation but also maintain near-identical Pass@1 scores compared to baselines trained on unprocessed code.

cs.SE↗

arXiv2025

PTMPicker: Facilitating Efficient Pretrained Model Selection for Application Developers

The rapid emergence of pretrained models (PTMs) has attracted significant attention from both Deep Learning (DL) researchers and downstream application developers. However, selecting appropriate PTMs remains challenging because existing methods typically rely on keyword-based searches in which the keywords are often derived directly from function descriptions. This often fails to fully capture user intent and makes it difficult to identify suitable models when developers also consider factors such as bias mitigation, hardware requirements, or license compliance. To address the limitations of keyword-based model search, we propose PTMPicker to accurately identify suitable PTMs. We first define a structured template composed of common and essential attributes for PTMs and then PTMPicker represents both candidate models and user-intended features (i.e., model search requests) in this unified format. To determine whether candidate models satisfy user requirements, it computes embedding similarities for function-related attributes and uses well-crafted prompts to evaluate special constraints such as license compliance and hardware requirements. We scraped a total of 543,949 pretrained models from Hugging Face to prepare valid candidates for selection. PTMPicker then represented them in the predefined structured format by extracting their associated descriptions. Guided by the extracted metadata, we synthesized a total of 15,207 model search requests with carefully designed prompts, as no such search requests are readily available. Experiments on the curated PTM dataset and the synthesized model search requests show that PTMPicker can help users effectively identify models,with 85% of the sampled requests successfully locating appropriate PTMs within the top-10 ranked candidates.

cs.SE↗

arXiv2025

LLMAID: Identifying AI Capabilities in Android Apps with LLMs

Recent advancements in artificial intelligence (AI) and its widespread integration into mobile software applications have received significant attention, highlighting the growing prominence of AI capabilities in modern software systems. However, the inherent hallucination and reliability issues of AI continue to raise persistent concerns. Consequently, application users and regulators increasingly ask critical questions such as: Does the application incorporate AI capabilities? and What specific types of AI functionalities are embedded? Preliminary efforts have been made to identify AI capabilities in mobile software; however, existing approaches mainly rely on manual inspection and rule-based heuristics. These methods are not only costly and time-consuming but also struggle to adapt advanced AI techniques. To address the limitations of existing methods, we propose LLMAID (Large Language Model for AI Discovery). LLMAID includes four main tasks: (1) candidate extraction, (2) knowledge base interaction, (3) AI capability analysis and detection, and (4) AI service summarization. We apply LLMAID to a dataset of 4,201 Android applications and demonstrate that it identifies 242% more real-world AI apps than state-of-the-art rule-based approaches. Our experiments show that LLM4AID achieves high precision and recall, both exceeding 90%, in detecting AI-related components. Additionally, a user study indicates that developers find the AI service summaries generated by LLMAID to be more informative and preferable to the original app descriptions. Finally, we leverage LLMAID to perform an empirical analysis of AI capabilities across Android apps. The results reveal a strong concentration of AI functionality in computer vision (54.80%), with object detection emerging as the most common task (25.19%).

cs.SE↗

arXiv2025

Optimizing Knowledge Utilization for Multi-Intent Comment Generation with Large Language Models

Code comment generation aims to produce a generic overview of a code snippet, helping developers understand and maintain code. However, generic summaries alone are insufficient to meet the diverse needs of practitioners; for example, developers expect the implementation insights to be presented in an untangled manner, while users seek clear usage instructions. This highlights the necessity of multi-intent comment generation. With the widespread adoption of Large Language Models (LLMs) for code-related tasks, these models have been leveraged to tackle the challenge of multi-intent comment generation. Despite their successes, state-of-the-art LLM-based approaches often struggle to construct correct relationships among intents, code, and comments within a smaller number of demonstration examples. To mitigate this issue, we propose a framework named KUMIC for multi-intent comment generation. Built upon in-context learning, KUMIC leverages Chain-of-Thought (CoT) to optimize knowledge utilization for LLMs to generate intent-specific comments. Specifically, KUMIC first designs a retrieval mechanism to obtain similar demonstration examples, which exhibit high code-comment consistency. Then, KUMIC leverages CoT to guide LLMs to focus on statements facilitating the derivation of code comments aligned with specific intents. In this context, KUMIC constructs a mapping knowledge chain, linking code to intent-specific statements to comments, which enables LLMs to follow similar reasoning steps when generating the desired comments. We conduct extensive experiments to evaluate KUMIC, and the results demonstrate that KUMIC outperforms state-of-the-art baselines by 14.49\%, 22.41\%, 20.72\%, and 12.94\% in terms of BLEU, METEOR, ROUGE-L, and SBERT, respectively.

cs.SE↗

arXiv2025

LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead

The rapid integration of Large Language Models (LLMs) into software engineering (SE) has revolutionized tasks like code generation, producing a massive volume of software artifacts. This surge has exposed a critical bottleneck: the lack of scalable, reliable methods to evaluate these outputs. Human evaluation is costly and time-consuming, while traditional automated metrics like BLEU fail to capture nuanced quality aspects. In response, the LLM-as-a-Judge paradigm - using LLMs for automated evaluation - has emerged. This approach leverages the advanced reasoning of LLMs, offering a path toward human-like nuance at automated scale. However, LLM-as-a-Judge research in SE is still in its early stages. This forward-looking SE 2030 paper aims to steer the community toward advancing LLM-as-a-Judge for evaluating LLM-generated software artifacts. We provide a literature review of existing SE studies, analyze their limitations, identify key research gaps, and outline a detailed roadmap. We envision these frameworks as reliable, robust, and scalable human surrogates capable of consistent, multi-faceted artifact evaluation by 2030. Our work aims to foster research and adoption of LLM-as-a-Judge frameworks, ultimately improving the scalability of software artifact evaluation.

cs.SE↗

arXiv2025

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnerabilities through graphical interfaces remains largely unexplored. We present HackWorld, the first framework for systematically evaluating CUAs' capabilities to exploit web application vulnerabilities via visual interaction. Unlike sanitized benchmarks, HackWorld includes 36 real-world applications across 11 frameworks and 7 languages, featuring realistic flaws such as injection vulnerabilities, authentication bypasses, and unsafe input handling. Using a Capture-the-Flag (CTF) setup, it tests CUAs' capacity to identify and exploit these weaknesses while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals concerning trends: exploitation rates below 12% and low cybersecurity awareness. CUAs often fail at multi-step attack planning and misuse security tools. These results expose the current limitations of CUAs in web security contexts and highlight opportunities for developing more security-aware agents capable of effective vulnerability detection and exploitation.

cs.CR↗

arXiv2025

An Empirical Study of Vulnerabilities in Python Packages and Their Detection

In the rapidly evolving software development landscape, Python stands out for its simplicity, versatility, and extensive ecosystem. Python packages, as units of organization, reusability, and distribution, have become a pressing concern, highlighted by the considerable number of vulnerability reports. As a scripting language, Python often cooperates with other languages for performance or interoperability. This adds complexity to the vulnerabilities inherent to Python packages, and the effectiveness of current vulnerability detection tools remains underexplored. This paper addresses these gaps by introducing PyVul, the first comprehensive benchmark suite of Python-package vulnerabilities. PyVul includes 1,157 publicly reported, developer-verified vulnerabilities, each linked to its affected packages. To accommodate diverse detection techniques, it provides annotations at both commit and function levels. An LLM-assisted data cleansing method is incorporated to improve label accuracy, achieving 100% commit-level and 94% function-level accuracy, establishing PyVul as the most precise large-scale Python vulnerability benchmark. We further carry out a distribution analysis of PyVul, which demonstrates that vulnerabilities in Python packages involve multiple programming languages and exhibit a wide variety of types. Moreover, our analysis reveals that multi-lingual Python packages are potentially more susceptible to vulnerabilities. Evaluation of state-of-the-art detectors using this benchmark reveals a significant discrepancy between the capabilities of existing tools and the demands of effectively identifying real-world security issues in Python packages. Additionally, we conduct an empirical review of the top-ranked CWEs observed in Python packages, to diagnose the fine-grained limitations of current detection tools and highlight the necessity for future advancements in the field.

cs.SE↗

arXiv2025

The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget

Source code is usually formatted with elements like indentation and newlines to improve readability for human developers. However, these visual aids do not seem to be beneficial for large language models (LLMs) in the same way since the code is processed as a linear sequence of tokens. Furthermore, these additional tokens can lead to increased computational costs and longer response times for LLMs. If such formatting elements are non-essential to LLMs, we can reduce such costs by removing them from the code. To figure out the role played by formatting elements, we conduct a comprehensive empirical study to evaluate the impact of code formatting on LLM performance and efficiency. Through large-scale experiments on Fill-in-the-Middle Code Completion tasks across four programming languages (Java, Python, C++, C\#) and ten LLMs-including both commercial and open-source models-we systematically analyze token count and performance when formatting elements are removed. Key findings indicate that LLMs can maintain performance across formatted code and unformatted code, achieving an average input token reduction of 24.5\% with negligible output token reductions. This makes code format removal a practical optimization strategy for improving LLM efficiency. Further exploration reveals that both prompting and fine-tuning LLMs can lead to significant reductions (up to 36.1\%) in output code length without compromising correctness. To facilitate practical applications, we develop a bidirectional code transformation tool for format processing, which can be seamlessly integrated into existing LLM inference workflows, ensuring both human readability and LLM efficiency.

cs.SE↗

arXiv2025

Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers

Machine learning (ML) for text classification has been widely used in various domains. These applications can significantly impact ethics, economics, and human behavior, raising serious concerns about trusting ML decisions. Studies indicate that conventional metrics are insufficient to build human trust in ML models. These models often learn spurious correlations and predict based on them. In the real world, their performance can deteriorate significantly. To avoid this, a common practice is to test whether predictions are reasonable based on valid patterns in the data. Along with this, a challenge known as the trustworthiness oracle problem has been introduced. Due to the lack of automated trustworthiness oracles, the assessment requires manual validation of the decision process disclosed by explanation methods. However, this is time-consuming, error-prone, and unscalable. We propose TOKI, the first automated trustworthiness oracle generation method for text classifiers. TOKI automatically checks whether the words contributing the most to a prediction are semantically related to the predicted class. Specifically, we leverage ML explanations to extract the decision-contributing words and measure their semantic relatedness with the class based on word embeddings. We also introduce a novel adversarial attack method that targets trustworthiness vulnerabilities identified by TOKI. To evaluate their alignment with human judgement, experiments are conducted. We compare TOKI with a naive baseline based solely on model confidence and TOKI-guided adversarial attack method with A2T, a SOTA adversarial attack method. Results show that relying on prediction uncertainty cannot effectively distinguish between trustworthy and untrustworthy predictions, TOKI achieves 142% higher accuracy than the naive baseline, and TOKI-guided attack method is more effective with fewer perturbations than A2T.

cs.SE↗

arXiv2025

PatchFuzz: Patch Fuzzing for JavaScript Engines

Patch fuzzing is a technique aimed at identifying vulnerabilities that arise from newly patched code. While researchers have made efforts to apply patch fuzzing to testing JavaScript engines with considerable success, these efforts have been limited to using ordinary test cases or publicly available vulnerability PoCs (Proof of Concepts) as seeds, and the sustainability of these approaches is hindered by the challenges associated with automating the PoC collection. To address these limitations, we propose an end-to-end sustainable approach for JavaScript engine patch fuzzing, named PatchFuzz. It automates the collection of PoCs of a broader range of historical vulnerabilities and leverages both the PoCs and their corresponding patches to uncover new vulnerabilities more effectively. PatchFuzz starts by recognizing git commits which intend to fix security bugs. Subsequently, it extracts and processes PoCs from these commits to form the seeds for fuzzing, while utilizing code revisions to focus limited fuzzing resources on the more vulnerable code areas through selective instrumentation. The mutation strategy of PatchFuzz is also optimized to maximize the potential of the PoCs. Experimental results demonstrate the effectiveness of PatchFuzz. Notably, 54 bugs across six popular JavaScript engines have been exposed and a total of $62,500 bounties has been received.

cs.CR↗