arXiv subjects

Kehui Chen

Publications and source records attributed to Kehui Chen.

10 recordsLinked to original sources

arXiv2026

Teaching Software Engineering with LLM and MCP Integration: From Classroom to Industry Practice

The rapid integration of Large Language Models (LLMs) and the Model Context Protocol (MCP) into industrial software engineering has created a pressing need to update software engineering education to align with emerging technologies and evolving industry demands. This study investigates an innovative approach that integrates LLMs and MCP into a collaborative teaching model for software engineering education, aiming to build a practical learning framework closely connected to real-world engineering practices. By embedding LLM and MCP driven tools into daily teaching, code assistance, and engineering simulations, the model effectively bridges the gap between traditional instruction and industrial workflows. This integration enhances students' programming competence, practical problem-solving abilities, and proficiency in using intelligent engineering tools. Furthermore, through partnerships with industry internships, students can apply these technologies in real-world settings, further strengthening the connection between academic preparation and professional practice. Overall, this research offers a practical pathway for reforming and innovating software engineering education in the era of artificial intelligence.

cs.SE↗

arXiv2026

Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering

Large Language Models (LLMs) are increasingly used in AI-based software engineering, but their limitations in complex task execution and multi-tool coordination have driven growing interest in the Model Context Protocol (MCP). Existing research has mainly focused on MCP's technical design, with limited empirical evidence on how it is adopted and used in enterprise practice, particularly with regard to deployment challenges, operational risks, and practitioner expectations. To address this gap, we conducted semi-structured interviews with 20 practitioners from eight companies in the Internet and financial sectors. The findings show that MCP is valued for supporting cross-system collaboration, task decoupling, and knowledge reuse in LLM-based workflows, but its adoption remains constrained by ecosystem fragmentation, cross-component coordination difficulties, and unresolved problems in distributed state management and fault diagnosis. Participants also expressed strong demand for better standardization, lower adoption barriers through low-code or plugin-based approaches, and more systematic operational support. These results provide early empirical evidence on enterprise MCP practice and offer practical implications for improving MCP's standardization, usability, and deployment readiness in real-world software engineering environments.

cs.SE↗

arXiv2026

Making Sense of Scams: Understanding Scam Conversations Through Multi-Level Alignment

Online scams often unfold gradually through interaction, yet existing detection systems predominantly rely on snapshot-based signals and interruptive warnings, revealing two research gaps in the lack of signals that represent scam risk within conversational dynamics and the underexplored design of non-interruptive interaction. To address these gaps, we introduce multi-level alignment-based hints, informed by the Interactive Alignment Model, as a new detection signal for supporting sensemaking in scam-related conversations. These hints operationalize low-level lexical and syntactic alignments and high-level semantic and situation-model alignments between conversational participants, making conversational dynamics visible to users. We first conduct a preliminary evaluation on real-life scam dialogues, showing that as conversations approach scam attempts, low-level alignment scores remain stable while high-level alignment scores systematically decline, revealing a consistent cross-level pattern indicative of scam progression. Building on this insight, we conduct a user study with thirty participants, indicating that relative to the no-hint baseline, multi-level alignment-based hints increase precision by 0.25, recall by 0.16, and F1 score by 0.21, yielding substantially larger gains than the marginal improvements achieved by keyword-triggered alerts. Statistical analyses reveal that the proposed hints support earlier and more stable confidence formation over time, with ablation results further highlighting the effectiveness of combining alignment hints across levels in achieving these advantages.

cs.HC↗

arXiv2026

R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability

Accurate requirement-to-code traceability is crucial for software maintenance. However, existing IR- and embedding-based methods are heavily dependent on lexical similarity, often yielding incomplete or inconsistent links across projects and languages and incurring high cost from long-context retrieval and prompting. This paper presents R2Code, an LLM-based semantic traceability framework designed to improve trace link accuracy while reducing inference cost. R2Code integrates three components: 1) a decomposition-enhanced Bidirectional Alignment Network (BAN) that aligns four-layer requirement semantics with corresponding code structures to support cross-level semantic matching; 2) a Self-Reflective Consistency Verification (SRCV) module that conducts explanation-guided consistency checking to calibrate link reliability; and 3) a Dynamic Context-Adaptive Retrieval (DCAR) mechanism that adjusts retrieval granularity and filters contexts using semantic-overlap weighting for efficient context utilization. Experiments on five public datasets spanning multiple domains and two programming languages demonstrate that R2Code consistently outperforms the strongest baselines, achieving an average F1 gain of 7.4%, while reducing token consumption by up to 41.7% through adaptive context control.

cs.SE↗

arXiv2024

FinTextQA: A Dataset for Long-form Financial Question Answering

Accurate evaluation of financial question answering (QA) systems necessitates a comprehensive dataset encompassing diverse question types and contexts. However, current financial QA datasets lack scope diversity and question complexity. This work introduces FinTextQA, a novel dataset for long-form question answering (LFQA) in finance. FinTextQA comprises 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.Moreover, we developed a Retrieval-Augmented Generation (RAG)-based LFQA system, comprising an embedder, retriever, reranker, and generator. A multi-faceted evaluation approach, including human ranking, automatic metrics, and GPT-4 scoring, was employed to benchmark the performance of different LFQA system configurations under heightened noisy conditions. The results indicate that: (1) Among all compared generators, Baichuan2-7B competes closely with GPT-3.5-turbo in accuracy score; (2) The most effective system configuration on our dataset involved setting the embedder, retriever, reranker, and generator as Ada2, Automated Merged Retrieval, Bge-Reranker-Base, and Baichuan2-7B, respectively; (3) models are less susceptible to noise after the length of contexts reaching a specific threshold.

cs.CL↗

arXiv2024

Least Squares Inference for Data with Network Dependency

We address the inference problem concerning regression coefficients in a classical linear regression model using least squares estimates. The analysis is conducted under circumstances where network dependency exists across units in the sample. Neglecting the dependency among observations may lead to biased estimation of the asymptotic variance and often inflates the Type I error in coefficient inference. In this paper, we first establish a central limit theorem for the ordinary least squares estimate, with a verifiable dependence condition alongside corresponding neighborhood growth conditions. Subsequently, we propose a consistent estimator for the asymptotic variance of the estimated coefficients, which employs a data-driven method to balance the bias-variance trade-off. We find that the optimal tuning depends on the linear hypothesis under consideration and must be chosen adaptively. The presented theory and methods are illustrated and supported by numerical experiments and a data example.

stat.ME↗

arXiv2020

Nonparametric covariance estimation for mixed longitudinal studies, with applications in midlife women's health

In mixed longitudinal studies, a group of subjects enter the study at different ages (cross-sectional) and are followed for successive years (longitudinal). In the context of such studies, we consider nonparametric covariance estimation with samples of noisy and partially observed functional trajectories. The proposed algorithm is based on a noniterative sequential-aggregation scheme with only basic matrix operations and closed-form solutions in each step. The good performance of the proposed method is supported by both theory and numerical experiments. We also apply the proposed procedure to a study on the working memory of midlife women, based on data from the Study of Women's Health Across the Nation (SWAN).

stat.ME↗

arXiv2018

A test of weak separability for multi-way functional data, with application to brain connectivity studies

This paper concerns the modeling of multi-way functional data where double or multiple indices are involved. We introduce a concept of weak separability. The weakly separable structure supports the use of factorization methods that decompose the signal into its spatial and temporal components. The analysis reveals interesting connections to the usual strongly separable covariance structure, and provides insights into tensor methods for multi-way functional data. We propose a formal test for the weak separability hypothesis, where the asymptotic null distribution of the test statistic is a chi-square type mixture. The method is applied to study brain functional connectivity derived from source localized magnetoencephalography signals during motor tasks.

stat.ME↗

arXiv2015

Network Cross-Validation for Determining the Number of Communities in Network Data

The stochastic block model and its variants have been a popular tool in analyzing large network data with community structures. In this paper we develop an efficient network cross-validation (NCV) approach to determine the number of communities, as well as to choose between the regular stochastic block model and the degree corrected block model. The proposed NCV method is based on a block-wise node-pair splitting technique, combined with an integrated step of community recovery using sub-blocks of the adjacency matrix. We prove that the probability of under selection vanishes as the number of node increases, under mild conditions satisfied by a wide range of popular community recovery algorithms. The solid performance of our method is also demonstrated in extensive simulations and a data example.

stat.ME↗

arXiv2015

Localized Functional Principal Component Analysis

We propose localized functional principal component analysis (LFPCA), looking for orthogonal basis functions with localized support regions that explain most of the variability of a random process. The LFPCA is formulated as a convex optimization problem through a novel Deflated Fantope Localization method and is implemented through an efficient algorithm to obtain the global optimum. We prove that the proposed LFPCA converges to the original FPCA when the tuning parameters are chosen appropriately. Simulation shows that the proposed LFPCA with tuning parameters chosen by cross validation can almost perfectly recover the true eigenfunctions and significantly improve the estimation accuracy when the eigenfunctions are truly supported on some subdomains. In the scenario that the original eigenfunctions are not localized, the proposed LFPCA also serves as a nice tool in finding orthogonal basis functions that balance between interpretability and the capability of explaining variability of the data. The analyses of a country mortality data and a growth curve data reveal interesting features that cannot be found by standard FPCA methods.

stat.ME↗