arXiv subjects

Pinjia He

Publications and source records attributed to Pinjia He.

At least 37 records · Page 2Linked to original sources

arXiv2026

MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning

Log parsing converts semi-structured logs into structured templates, forming a critical foundation for downstream analysis. Traditional syntax and semantic-based parsers often struggle with semantic variations in evolving logs and data scarcity stemming from their limited domain coverage. Recent large language model (LLM)-based parsers leverage in-context learning (ICL) to extract semantics from examples, demonstrating superior accuracy. However, LLM-based parsers face two main challenges: 1) underutilization of ICL capabilities, particularly in dynamic example selection and cross-domain generalization, leading to inconsistent performance; 2) time-consuming and costly LLM querying. To address these challenges, we present MicLog, the first progressive meta in-context learning (ProgMeta-ICL) log parsing framework that combines meta-learning with ICL on small open-source LLMs (i.e., Qwen-2.5-3B). Specifically, MicLog: i) enhances LLMs' ICL capability through a zero-shot to k-shot ProgMeta-ICL paradigm, employing weighted DBSCAN candidate sampling and enhanced BM25 demonstration selection; ii) accelerates parsing via a multi-level pre-query cache that dynamically matches and refines recently parsed templates. Evaluated on Loghub-2.0, MicLog achieves 10.3% higher parsing accuracy than the state-of-the-art parser while reducing parsing time by 42.4%.

cs.SE↗

arXiv2025

Rethinking the Evaluation of Microservice RCA with a Fault Propagation-Aware Benchmark

While cloud-native microservice architectures have revolutionized software development, their inherent operational complexity makes failure Root Cause Analysis (RCA) a critical yet challenging task. Numerous data-driven RCA models have been proposed to address this challenge. However, we find that the benchmarks used to evaluate these models are often too simple to reflect real-world scenarios. Our preliminary study reveals that simple rule-based methods can achieve performance comparable to or even surpassing state-of-the-art (SOTA) models on four widely used public benchmarks. This finding suggests that the oversimplification of existing benchmarks might lead to an overestimation of the performance of RCA methods. To further investigate the oversimplification issue, we conduct a systematic analysis of popular public RCA benchmarks, identifying key limitations in their fault injection strategies, call graph structures, and telemetry signal patterns. Based on these insights, we propose an automated framework for generating more challenging and comprehensive benchmarks that include complex fault propagation scenarios. Our new dataset contains 1,430 validated failure cases from 9,152 fault injections, covering 25 fault types across 6 categories, dynamic workloads, and hierarchical ground-truth labels that map failures from services down to code-level causes. Crucially, to ensure the failure cases are relevant to IT operations, each case is validated to have a discernible impact on user-facing SLIs. Our re-evaluation of 11 SOTA models on this new benchmark shows that they achieve low Top@1 accuracies, averaging 0.21, with the best-performing model reaching merely 0.37, and execution times escalating from seconds to hours.

cs.SE↗

arXiv2025

BackportBench: A Multilingual Benchmark for Automated Backporting of Patches

Many modern software projects evolve rapidly to incorporate new features and security patches. It is important for users to update their dependencies to safer versions, but many still use older, vulnerable package versions because upgrading can be difficult and may break their existing codebase. Software developers can mitigate this problem by backporting security patches to older releases. However, manually backporting is time-consuming and error-prone. The effectiveness of existing automated backporting techniques on general software remains unclear since they typically target only code-hunk or function-level patch porting scenarios and are evaluated with imperfect metrics. To facilitate the development and evaluation of automated backporting techniques, we introduce BackportBench, the first comprehensive benchmark suite for patch backporting problem. BackportBench is a multilingual benchmark that contains 202 patch backporting problems from PyPI, Maven, and npm, each with executable Docker environments and relevant test cases. We evaluated existing patch porting methods and LLM-based techniques that have the potential to adapt to this task using BackportBench. The results show that the agentic method has outperformed traditional patch porting methods, especially on cases that require logical and structural changes. However, the performance varies across different programming languages. Based on the findings, we draw several implications for researchers and software practitioners in future work on automated backporting.

cs.SE↗

arXiv2025

DynaCausal: Dynamic Causality-Aware Root Cause Analysis for Distributed Microservices

Cloud-native microservices enable rapid iteration and scalable deployment but also create complex, fast-evolving dependencies that challenge reliable diagnosis. Existing root cause analysis (RCA) approaches, even with multi-modal fusion of logs, traces, and metrics, remain limited in capturing dynamic behaviors and shifting service relationships. Three critical challenges persist: (i) inadequate modeling of cascading fault propagation, (ii) vulnerability to noise interference and concept drift in normal service behavior, and (iii) over-reliance on service deviation intensity that obscures true root causes. To address these challenges, we propose DynaCausal, a dynamic causality-aware framework for RCA in distributed microservice systems. DynaCausal unifies multi-modal dynamic signals to capture time-varying spatio-temporal dependencies through interaction-aware representation learning. It further introduces a dynamic contrastive mechanism to disentangle true fault indicators from contextual noise and adopts a causal-prioritized pairwise ranking objective to explicitly optimize causal attribution. Comprehensive evaluations on public benchmarks demonstrate that DynaCausal consistently surpasses state-of-the-art methods, attaining an average AC@1 of 0.63 with absolute gains from 0.25 to 0.46, and delivering both accurate and interpretable diagnoses in highly dynamic microservice environments.

cs.SE↗

arXiv2025

CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Series

Multivariate time series (MTS) anomaly detection is essential for maintaining the reliability of industrial systems, yet real-world deployment is hindered by two critical challenges: training data contamination (noises and hidden anomalies) and inefficient model inference. Existing unsupervised methods assume clean training data, but contamination distorts learned patterns and degrades detection accuracy. Meanwhile, complex deep models often overfit to contamination and suffer from high latency, limiting practical use. To address these challenges, we propose CLEANet, a robust and efficient anomaly detection framework in contaminated multivariate time series. CLEANet introduces a Contamination-Resilient Training Framework (CRTF) that mitigates the impact of corrupted samples through an adaptive reconstruction weighting strategy combined with clustering-guided contrastive learning, thereby enhancing robustness. To further avoid overfitting on contaminated data and improve computational efficiency, we design a lightweight conjugate MLP that disentangles temporal and cross-feature dependencies. Across five public datasets, CLEANet achieves up to 73.04% higher F1 and 81.28% lower runtime compared with ten state-of-the-art baselines. Furthermore, integrating CRTF into three advanced models yields an average 5.35% F1 gain, confirming its strong generalizability.

cs.LG↗

arXiv2025

A Goal-Driven Survey on Root Cause Analysis

Root Cause Analysis (RCA) is a crucial aspect of incident management in large-scale cloud services. While the term root cause analysis or RCA has been widely used, different studies formulate the task differently. This is because the term "RCA" implicitly covers tasks with distinct underlying goals. For instance, the goal of localizing a faulty service for rapid triage is fundamentally different from identifying a specific functional bug for a definitive fix. However, previous surveys have largely overlooked these goal-based distinctions, conventionally categorizing papers by input data types (e.g., metric-based vs. trace-based methods). This leads to the grouping of works with disparate objectives, thereby obscuring the true progress and gaps in the field. Meanwhile, the typical audience of an RCA survey is either laymen who want to know the goals and big picture of the task or RCA researchers who want to figure out past research under the same task formulation. Thus, an RCA survey that organizes the related papers according to their goals is in high demand. To this end, this paper presents a goal-driven framework that effectively categorizes and integrates 135 papers on RCA in the context of cloud incident management based on their diverse goals, spanning the period from 2014 to 2025. In addition to the goal-driven categorization, it discusses the ultimate goal of all RCA papers as an umbrella covering different RCA formulations. Moreover, the paper discusses open challenges and future directions in RCA.

cs.SE↗

arXiv2025

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users' questions, it would actively watch people's behavior and their environment to detect potential dangers in advance. Our Proactive Safety Bench (PaSBench) evaluates this capability through 416 multimodal scenarios (128 image sequences, 288 text logs) spanning 5 safety-critical domains. Evaluation of 36 advanced models reveals fundamental limitations: Top performers like Gemini-2.5-pro achieve 71% image and 64% text accuracy, but miss 45-55% risks in repeated trials. Through failure analysis, we identify unstable proactive reasoning rather than knowledge deficits as the primary limitation. This work establishes (1) a proactive safety benchmark, (2) systematic evidence of model limitations, and (3) critical directions for developing reliable protective AI. We believe our dataset and findings can promote the development of safer AI assistants that actively prevent harm rather than merely respond to requests. Our dataset can be found at https://huggingface.co/datasets/Youliang/PaSBench.

cs.CL↗

arXiv2025

SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints

The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resolution and feature addition. Existing AI for software engineering leaderboards (e.g., SWE-bench) focus solely on solution accuracy, ignoring the crucial factor of effectiveness in a resource-constrained world. This is a universal problem that also exists beyond software engineering tasks: any AI system should be more than correct - it must also be cost-effective. To address this gap, we introduce SWE-Effi, a set of new metrics to re-evaluate AI systems in terms of holistic effectiveness scores. We define effectiveness as the balance between the accuracy of outcome (e.g., issue resolve rate) and the resources consumed (e.g., token and time). In this paper, we specifically focus on the software engineering scenario by re-ranking popular AI systems for issue resolution on a subset of the SWE-bench benchmark using our new multi-dimensional metrics. We found that AI system's effectiveness depends not just on the scaffold itself, but on how well it integrates with the base model, which is key to achieving strong performance in a resource-efficient manner. We also identified systematic challenges such as the "token snowball" effect and, more significantly, a pattern of "expensive failures". In these cases, agents consume excessive resources while stuck on unsolvable tasks - an issue that not only limits practical deployment but also drives up the cost of failed rollouts during RL training. Lastly, we observed a clear trade-off between effectiveness under the token budget and effectiveness under the time budget, which plays a crucial role in managing project budgets and enabling scalable reinforcement learning, where fast responses are essential.

cs.SE↗

arXiv2025

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach

Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement learning (RL) offers a promising alternative. We propose a human-in-the-loop dual-actor fine-tuning framework grounded in RL. The framework integrates a primary actor for robust multi-task performance with a refinement actor for latent-space adaptation. Beyond standard physical interventions, we introduce a lightweight talk-and-tweak scheme that converts human corrections into semantically grounded language commands, thereby generating a new dataset for policy learning. In real-world multi-task experiments, our approach achieves 100% success across three tasks within 101 minutes of online fine-tuning. For long-horizon tasks, it sustains a 50% success rate over 12 consecutive operations. Furthermore, the framework scales effectively to multi-robot training, achieving up to a 2 times improvement in efficiency when using dual robots. The experiment videos are available at https://sites.google.com/view/hil-daft/.

cs.RO↗

arXiv2025

UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench

The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To address this challenge, we introduce UTGenerator, an LLM-driven test case generator that automatically analyzes codebases and dependencies to generate test cases for real-world Python projects. Building on UTGenerator, we propose UTBoost, a comprehensive framework for test case augmentation. In our evaluation, we identified 36 task instances with insufficient test cases and uncovered 345 erroneous patches incorrectly labeled as passed in the original SWE Bench. These corrections, impacting 40.9% of SWE-Bench Lite and 24.4% of SWE-Bench Verified leaderboard entries, yield 18 and 11 ranking changes, respectively.

cs.SE↗

arXiv2025

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs

Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images. However, ensuring the safety of these models remains a significant challenge, particularly in accurately identifying whether multimodal content is safe or unsafe-a capability we term safety awareness. In this paper, we introduce MMSafeAware, the first comprehensive multimodal safety awareness benchmark designed to evaluate MLLMs across 29 safety scenarios with 1500 carefully curated image-prompt pairs. MMSafeAware includes both unsafe and over-safety subsets to assess models abilities to correctly identify unsafe content and avoid over-sensitivity that can hinder helpfulness. Evaluating nine widely used MLLMs using MMSafeAware reveals that current models are not sufficiently safe and often overly sensitive; for example, GPT-4V misclassifies 36.1% of unsafe inputs as safe and 59.9% of benign inputs as unsafe. We further explore three methods to improve safety awareness-prompting-based approaches, visual contrastive decoding, and vision-centric reasoning fine-tuning-but find that none achieve satisfactory performance. Our findings highlight the profound challenges in developing MLLMs with robust safety awareness, underscoring the need for further research in this area. All the code and data will be publicly available to facilitate future research.

cs.CL↗

arXiv2025

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs

This paper explores the problem of commonsense level vision-knowledge conflict in Multimodal Large Language Models (MLLMs), where visual information contradicts model's internal commonsense knowledge. To study this issue, we introduce an automated framework, augmented with human-in-the-loop quality control, to generate inputs designed to simulate and evaluate these conflicts in MLLMs. Using this framework, we have crafted a diagnostic benchmark consisting of 374 original images and 1,122 high-quality question-answer (QA) pairs. The benchmark covers two aspects of conflict and three question types, providing a thorough assessment tool. We apply this benchmark to assess the conflict-resolution capabilities of nine representative MLLMs from various model families. Our results indicate an evident over-reliance on parametric knowledge for approximately 20% of all queries, especially among Yes-No and action-related problems. Based on these findings, we evaluate the effectiveness of existing approaches to mitigating the conflicts and compare them to our "Focus-on-Vision" prompting strategy. Despite some improvement, the vision-knowledge conflict remains unresolved and can be further scaled through our data construction framework. Our proposed framework, benchmark, and analysis contribute to the understanding and mitigation of vision-knowledge conflicts in MLLMs.

cs.CL↗

arXiv2025

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating unsafe content. We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position, significantly enhancing their safety capabilities. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence. Our empirical evaluation, conducted using LLaMA3 and Mistral model families across six attack scenarios, demonstrates that our method not only improves model safety without compromising performance but also surpasses baseline methods in defending against attacks.

cs.CL↗

arXiv2025

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models fail to robustly verify their own outputs. We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this. RISE explicitly and simultaneously trains an LLM to improve both its problem-solving and self-verification abilities within a single, integrated RL process. The core mechanism involves leveraging verifiable rewards from an outcome verifier to provide on-the-fly feedback for both solution generation and self-verification tasks. In each iteration, the model generates solutions, then critiques its own on-policy generated solutions, with both trajectories contributing to the policy update. Extensive experiments on diverse mathematical reasoning benchmarks show that RISE consistently improves model's problem-solving accuracy while concurrently fostering strong self-verification skills. Our analyses highlight the advantages of online verification and the benefits of increased verification compute. Additionally, RISE models exhibit more frequent and accurate self-verification behaviors during reasoning. These advantages reinforce RISE as a flexible and effective path towards developing more robust and self-aware reasoners.

cs.AI↗

arXiv2025

AL-Bench: A Benchmark for Automatic Logging

Logging, the practice of inserting log statements into source code, is critical for improving software reliability. Recently, language model-based techniques have been developed to automate log statement generation based on input code. While these tools show promising results in prior studies, the fairness of their results comparisons is not guaranteed due to the use of ad hoc datasets. In addition, existing evaluation approaches exclusively dependent on code similarity metrics fail to capture the impact of code diff on runtime logging behavior, as minor code modifications can induce program uncompilable and substantial discrepancies in log output semantics. To enhance the consistency and reproducibility of logging evaluation, we introduce AL-Bench, a comprehensive benchmark designed specifically for automatic logging tools. AL-Bench includes a large-scale, high-quality, diverse dataset collected from 10 widely recognized projects with varying logging requirements. Moreover, it introduces a novel dynamic evaluation methodology to provide a run-time perspective of logging quality in addition to the traditional static evaluation at source code level. Specifically, AL-Bench not only evaluates the similarity between the oracle and predicted log statements in source code, but also evaluates the difference between the log files printed by both log statements during runtime. AL-Bench reveals significant limitations in existing static evaluation, as all logging tools show average accuracy drops of 37.49%, 23.43%, and 15.80% in predicting log position, level, and message compared to their reported results. Furthermore, with dynamic evaluation, AL-Bench reveals that 20.1%-83.6% of these generated log statements are unable to compile. Moreover, the best-performing tool achieves only 21.32% cosine similarity between the log files of the oracle and generated log statements.

cs.SE↗

arXiv2025

Let AI Read First: Enhancing Reading Abilities for Individuals with Dyslexia through Artificial Intelligence

Dyslexia, a neurological condition affecting approximately 12% of the global population, presents significant challenges to reading ability and quality of life. Existing assistive technologies are limited by factors such as unsuitability for quiet environments, high costs, and the risk of distorting meaning or failing to provide real-time support. To address these issues, we introduce LARF (Let AI Read First), the first strategy that employs large language models to annotate text and enhance readability while preserving the original content. We evaluated LARF in a large-scale between-subjects experiment, involving 150 participants with dyslexia. The results show that LARF significantly improves reading performance and experience for individuals with dyslexia. Results also prove that LARF is particularly helpful for participants with more severe reading difficulties. Furthermore, this work discusses potential research directions opened up by LARF for the HCI community.

cs.HC↗

arXiv2025

Aligning the Objective of LLM-based Program Repair

Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of current infilling-style methods, which impedes LLMs from fully leveraging pre-trained knowledge for program repair. In addition, while some LLMs can locate and repair bugs in certain functions using the related artifacts (e.g., test cases), existing methods still depend on statement-level fault localization methods to provide a list of buggy hunks for repair. This restriction hinders LLMs from exploring potential patches beyond the given locations. In this paper, we investigate a new approach to adapt LLMs to program repair. Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective and allowing them to refine the whole program without first identifying faulty statements. Based on this insight, we designed D4C, a straightforward prompting framework for APR. D4C can repair 180 bugs correctly in Defects4J, with each patch being sampled only 10 times. This surpasses the SOTA APR methods with perfect fault localization by 10% and reduces the patch sampling number by 90%. Our findings reveal that (1) objective alignment is crucial for fully exploiting LLM's pre-trained capability, and (2) replacing the traditional localize-buggy-hunks-then-repair workflow with direct debugging is more effective for LLM-based APR methods. Thus, we believe this paper introduces a new mindset for harnessing LLMs in APR.

cs.SE↗

arXiv2024

On the Influence of Data Resampling for Deep Learning-Based Log Anomaly Detection: Insights and Recommendations

Numerous Deep Learning (DL)-based approaches have gained attention in software Log Anomaly Detection (LAD), yet class imbalance in training data remains a challenge, with anomalies often comprising less than 1% of datasets like Thunderbird. Existing DLLAD methods may underperform in severely imbalanced datasets. Although data resampling has proven effective in other software engineering tasks, it has not been explored in LAD. This study aims to fill this gap by providing an in-depth analysis of the impact of diverse data resampling methods on existing DLLAD approaches from two distinct perspectives. Firstly, we assess the performance of these DLLAD approaches across four datasets with different levels of class imbalance, and we explore the impact of resampling ratios of normal to abnormal data on DLLAD approaches. Secondly, we evaluate the effectiveness of the data resampling methods when utilizing optimal resampling ratios of normal to abnormal data. Our findings indicate that oversampling methods generally outperform undersampling and hybrid sampling methods. Data resampling on raw data yields superior results compared to data resampling in the feature space. These improvements are attributed to the increased attention given to important tokens. By exploring the resampling ratio of normal to abnormal data, we suggest generating more data for minority classes through oversampling while removing less data from majority classes through undersampling. In conclusion, our study provides valuable insights into the intricate relationship between data resampling methods and DLLAD. By addressing the challenge of class imbalance, researchers and practitioners can enhance DLLAD performance.

cs.SE↗