arXiv subjects

Ting Zhang

Publications and source records attributed to Ting Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Discerning minds or generic tutors? Evaluating instructional guidance capabilities in Socratic LLMs

The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. While prior research has primarily examined their ability to generate Socratic questions, it often overlooks a critical aspect: adaptively guiding learners in accordance with their cognitive states. This study moves beyond question generation to emphasize instructional guidance capability. We ask: Can LLMs emulate expert tutors who dynamically adjust strategies in response to learners' states? To investigate this, we propose GuideEval, a benchmark grounded in authentic educational dialogues that evaluates pedagogical guidance through a three-phase behavioral framework: (1) Perception, inferring learner states; (2) Orchestration, adapting instructional strategies; and (3) Elicitation, stimulating proper reflections. Empirical results indicate that existing LLMs often fail to provide effective adaptive scaffolding when learners experience confusion or require redirection. To complement the quantitative evaluation, we conduct a detailed failure case analysis, providing an intuitive understanding of these shortcomings. Furthermore, we introduce a behavior-guided finetuning strategy that leverages behavior-prompted instructional dialogues, substantially enhancing guidance performance. By shifting the focus from isolated content evaluation to learner-centered state-aware interaction, our work advocates a more dialogic paradigm for evaluating Socratic LLMs.

cs.CL↗

arXiv2025

CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

Minority languages in China, such as Tibetan, Uyghur, and Traditional Mongolian, face significant challenges due to their unique writing systems, which differ from international standards. This discrepancy has led to a severe lack of relevant corpora, particularly for supervised tasks like headline generation. To address this gap, we introduce a novel dataset, Chinese Minority Headline Generation (CMHG), which includes 100,000 entries for Tibetan, and 50,000 entries each for Uyghur and Mongolian, specifically curated for headline generation tasks. Additionally, we propose a high-quality test set annotated by native speakers, designed to serve as a benchmark for future research in this domain. We hope this dataset will become a valuable resource for advancing headline generation in Chinese minority languages and contribute to the development of related benchmarks.

cs.CL↗

arXiv2025

CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics

Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directly from GitHub, are essential for training machine learning models to detect these security flaws. However, these datasets frequently suffer from significant noise, typically 40% to 75%, due primarily to the automatic and indiscriminate labeling of all changes in vulnerability-fixing commits (VFCs) as vulnerability-related. This misclassification occurs because not all changes in a commit aimed at fixing vulnerabilities pertain to security threats; many are routine updates like bug fixes or test improvements. This paper introduces the first methodology that uses the Large Language Model (LLM) with a heuristic enhancement to automatically identify vulnerability-fixing changes from VFCs, achieving an F1-score of 0.82. VulSifter was applied to a large-scale study, where we conducted a crawl of 127,063 repositories on GitHub, resulting in the acquisition of 5,352,105 commits. VulSifter involves utilizing an LLM to comprehend code semantics and contextual information, while applying heuristics to filter out unrelated changes. We then developed CleanVul, a high-quality dataset comprising 8,198 functions using our LLM heuristic enhancement approach, demonstrating Correctness (90.6%) comparable to established datasets such as SVEN and PrimeVul. To evaluate the CleanVul dataset, we conducted experiments focusing on fine-tuning various LLMs on CleanVul and other high-quality datasets. Evaluation results reveal that LLMs fine-tuned on CleanVul not only exhibit enhanced accuracy but also superior generalization capabilities compared to those trained on uncleaned datasets. Specifically, models trained on CleanVul and tested on PrimeVul achieve accuracy higher than those trained and tested exclusively on PrimeVul.

cs.SE↗

arXiv2025

PatchSeeker: Mapping NVD Records to their Vulnerability-fixing Commits with LLM Generated Commits and Embeddings

Software vulnerabilities pose serious risks to modern software ecosystems. While the National Vulnerability Database (NVD) is the authoritative source for cataloging these vulnerabilities, it often lacks explicit links to the corresponding Vulnerability-Fixing Commits (VFCs). VFCs encode precise code changes, enabling vulnerability localization, patch analysis, and dataset construction. Automatically mapping NVD records to their true VFCs is therefore critical. Existing approaches have limitations as they rely on sparse, often noisy commit messages and fail to capture the deep semantics in the vulnerability descriptions. To address this gap, we introduce PatchSeeker, a novel method that leverages large language models to create rich semantic links between vulnerability descriptions and their VFCs. PatchSeeker generates embeddings from NVD descriptions and enhances commit messages by synthesizing detailed summaries for those that are short or uninformative. These generated messages act as a semantic bridge, effectively closing the information gap between natural language reports and low-level code changes. Our approach PatchSeeker achieves 59.3% higher MRR and 27.9% higher Recall@10 than the best-performing baseline, Prospector, on the benchmark dataset. The extended evaluation on recent CVEs further confirms PatchSeeker's effectiveness. Ablation study shows that both the commit message generation method and the selection of backbone LLMs make a positive contribution to PatchSeeker. We also discuss limitations and open challenges to guide future work.

cs.SE↗

arXiv2025

HiPrFlame-An ab initio based real-fluid modeling approach for high-pressure combustion-I. Rationale, methodology, and application to laminar premixed flames

High-pressure combustion is central to modern propulsion and power-generation systems, where operating pressures often exceed the critical point of working fluids, resulting in pronounced real-fluid effects that fundamentally alter thermodynamic and transport properties. High-pressure combustion is central to modern propulsion and power-generation systems, where operating pressures often exceed the critical point of working fluids, resulting in pronounced real-fluid effects that fundamentally alter thermodynamic and transport properties. Existing methods for quantifying real-fluid behaviors typically rely on empirical correlations, fitted potentials, and cubic equations of state, which lack the accuracy required for species coverage and extreme conditions encountered in combustion processes. As such, this study introduces HiPrFlame, a novel ab initio-based modeling framework for high-pressure combustion, designed to deliver unprecedented fidelity in real-fluid property prediction in high-pressure combustion modeling. HiPrFlame integrates third-order Virial EoS derived from ab initio intermolecular potentials, thereby real-fluid departure functions for real-fluid thermodynamics and Enskog theory for real-fluid transport properties, with all implemented within a versatile OpenFOAM architecture that can be used for 0-D to 3-D real-fluid modeling. To accelerate multidimensional simulations, artificial neural network surrogate models are trained on a comprehensive property database, enabling efficient real-fluid property updating. The framework is demonstrated through case studies of high-pressure hydrogen combustion, including homogeneous autoignition and one-dimensional laminar premixed flames. Results demonstrate that HiPrFlame accurately captures experimental data for both thermodynamic and transport properties, significantly outperforming traditional methods.

physics.flu-dyn↗

arXiv2025

Decomposition of global solutions of bi-laplacian Nonautonomous Schrödinger equations

We study the bi-Laplacian Schrödinger equation with a general interaction term, which may be linear or nonlinear and is allowed to be time-dependent. We show that global solutions to such equations decompose asymptotically into a free wave and a weakly localized component in all space dimensions. Moreover, in dimensions $n \geq 9$, we prove that the weakly localized component is in fact spatially localized. The proof is based on a suitably adapted construction of the Free Channel Wave Operator, building on the method recently developed in~\cite{SW20221}.

math.AP↗

arXiv2025

VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM

Open-source software (OSS) has experienced a surge in popularity, attributed to its collaborative development model and cost-effective nature. However, the adoption of specific software versions in development projects may introduce security risks when these versions bring along vulnerabilities. Current methods of identifying vulnerable versions typically analyze and extract the code features involved in vulnerability patches using static analysis with pre-defined rules. They then use code clone detection to identify the vulnerable versions. These methods are hindered by imprecision due to (1) the exclusion of vulnerability-irrelevant code in the analysis and (2) the inadequacy of code clone detection. This paper presents VERCATION, an approach designed to identify vulnerable versions of OSS written in C/C++. VERCATION combines program slicing with a Large Language Model (LLM) to identify vulnerability-relevant code from vulnerability patches. It then backtracks historical commits to gather previous modifications of identified vulnerability-relevant code. We propose code clone detection based on expanded and normalized ASTs to compare the differences between pre-modification and post-modification code, thereby locating the vulnerability-introducing commit (vic) and enabling the identification of the vulnerable versions between the vulnerability-fixing commit and the vic. We curate a dataset linking 122 OSS vulnerabilities and 1,211 versions to evaluate VERCATION. On this dataset, our approach achieves an F1 score of 93.1%, outperforming current state-of-the-art methods. More importantly, VERCATION detected 202 incorrect vulnerable OSS versions in NVD reports.

cs.SE↗

arXiv2025

R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation

Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method that combines reinforcement learning from AI feedback (RLAIF) and structured reasoning distillation to teach small code LLMs to detect vulnerabilities while generating security-aware explanations. Unlike prior chain-of-thought and instruction tuning approaches, R2Vul rewards well-founded over deceptively plausible vulnerability explanations through RLAIF, which results in more precise detection and high-quality reasoning generation. To support RLAIF, we construct the first multilingual preference dataset for vulnerability detection, comprising 18,000 high-quality samples in C\#, JavaScript, Java, Python, and C. We evaluate R2Vul across five programming languages and against four static analysis tools, eight state-of-the-art LLM-based baselines, and various fine-tuning approaches. Our results demonstrate that a 1.5B R2Vul model exceeds the performance of its 32B teacher model and leading commercial LLMs such as Claude-4-Opus. Furthermore, we introduce a lightweight calibration step that reduces false positive rates under varying imbalanced data distributions. Finally, through qualitative analysis, we show that both LLM and human evaluators consistently rank R2Vul model's reasoning higher than other reasoning-based baselines.

cs.SE↗

arXiv2025

From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation

Large Language Models (LLMs) have demonstrated remarkable capabilities in mathematical problem-solving. However, the transition from providing answers to generating high-quality educational questions presents significant challenges that remain underexplored. To advance Educational Question Generation (EQG) and facilitate LLMs in generating pedagogically valuable and educationally effective questions, we introduce EQGBench, a comprehensive benchmark specifically designed for evaluating LLMs' performance in Chinese EQG. EQGBench establishes a five-dimensional evaluation framework supported by a dataset of 900 evaluation samples spanning three fundamental middle school disciplines: mathematics, physics, and chemistry. The dataset incorporates user queries with varying knowledge points, difficulty gradients, and question type specifications to simulate realistic educational scenarios. Through systematic evaluation of 46 mainstream large models, we reveal significant room for development in generating questions that reflect educational value and foster students' comprehensive abilities.

cs.CL↗

arXiv2025

ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices

Wearable AI systems aim to provide timely assistance in daily life, but existing approaches often rely on user initiation or predefined task knowledge, neglecting users' current mental states. We introduce ProMemAssist, a smart glasses system that models a user's working memory (WM) in real-time using multi-modal sensor signals. Grounded in cognitive theories of WM, our system represents perceived information as memory items and episodes with encoding mechanisms, such as displacement and interference. This WM model informs a timing predictor that balances the value of assistance with the cost of interruption. In a user study with 12 participants completing cognitively demanding tasks, ProMemAssist delivered more selective assistance and received higher engagement compared to an LLM baseline system. Qualitative feedback highlights the benefits of WM modeling for nuanced, context-sensitive support, offering design implications for more attentive and user-aware proactive agents.

cs.HC↗

arXiv2025

PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision boundary and perform uncertainty or diversity estimation, subsequently identifying potential high-quality samples. In few-shot scenarios, the empirical distribution often diverges significantly from the target distribution, causing the decision boundary to shift away from its optimal position. However, existing methods overlook the role of unlabeled samples in enhancing the empirical distribution to better align with the target distribution, resulting in a suboptimal decision boundary and the selection of samples that inadequately represent the target distribution. To address this, we propose a hybrid AL framework, termed \textbf{PromptAL} (Sample-Aware Dynamic Soft \textbf{Prompts} for Few-Shot \textbf{A}ctive \textbf{L}earning). This framework accounts for the contribution of each unlabeled data point in aligning the current empirical distribution with the target distribution, thereby optimizing the decision boundary. Specifically, PromptAL first leverages unlabeled data to construct sample-aware dynamic soft prompts that adjust the model's predictive distribution and decision boundary. Subsequently, based on the adjusted decision boundary, it integrates uncertainty estimation with both global and local diversity to select high-quality samples that more accurately represent the target distribution. Experimental results on six in-domain and three out-of-domain datasets show that PromptAL achieves superior performance over nine baselines. Our codebase is openly accessible.

cs.CL↗

arXiv2025

VulCoCo: A Simple Yet Effective Method for Detecting Vulnerable Code Clones

Code reuse is common in modern software development, but it can also spread vulnerabilities when developers unknowingly copy risky code. The code fragments that preserve the logic of known vulnerabilities are known as vulnerable code clones (VCCs). Detecting those VCCs is a critical but challenging task. Existing VCC detection tools often rely on syntactic similarity or produce coarse vulnerability predictions without clear explanations, limiting their practical utility. In this paper, we propose VulCoCo, a lightweight and scalable approach that combines embedding-based retrieval with large language model (LLM) validation. Starting from a set of known vulnerable functions, we retrieve syntactically or semantically similar candidate functions from a large corpus and use an LLM to assess whether the candidates retain the vulnerability. Given that there is a lack of reproducible vulnerable code clone benchmarks, we first construct a synthetic benchmark that spans various clone types. Our experiments on the benchmark show that VulCoCo outperforms prior state-of-the-art methods in terms of Precision@k and mean average precision (MAP). In addition, we also demonstrate VulCoCo's effectiveness in real-world projects by submitting 400 pull requests (PRs) to 284 open-source projects. Among them, 75 PRs were merged, and 15 resulted in newly published CVEs. We also provide insights to inspire future work to further improve the precision of vulnerable code clone detection.

cs.SE↗

arXiv2025

Downregulation of aquaporin 3 promotes hyperosmolarity-induced apoptosis of nucleus pulposus cells through PI3K/Akt/mTOR pathway suppression

Hyperosmolarity is a key contributor to nucleus pulposus cell (NPC) apoptosis during intervertebral disc degeneration (IVDD). Aquaporin 3 (AQP3), a membrane channel protein, regulates cellular osmotic balance by transporting water and osmolytes. Although AQP3 downregulation is associated with disc degeneration, its role in apoptosis under hyperosmotic conditions remains unclear. Here, we demonstrate that hyperosmolarity induces AQP3 depletion, suppresses the PI3K/AKT/mTOR signaling pathway, and promotes mitochondrial dysfunction and ROS accumulation in NPCs. Lentiviral overexpression of AQP3 restores this pathway, attenuates oxidative damage, and reduces apoptosis, preserving disc structure in IVDD rat models. In contrast, pharmacological inhibition of AQP3 exacerbates ECM catabolism and NP tissue loss. Our findings reveal that AQP3 deficiency under hyperosmolarity contributes to NPC apoptosis via suppression of PI3K/AKT/mTOR signaling, potentially creating a pathological cycle of disc degeneration. These results highlight AQP3 as a promising therapeutic target for IVDD.

q-bio.BM↗

arXiv2025

Fair Rate Maximization for Fluid Antenna Relay (FAR)-assisted Multi-user MISO Communications

In this paper, we investigate the problem of max-min rate maximization in fluid antenna relay (FAR)-assisted multi-user uplink multiple-input single-output (MISO) wireless systems, where each user is equipped with a single fluid antenna (FA) and the base station (BS) is equipped with multiple FAs. Unlike most existing relevant work focusing on maximizing sum rate of the fluid antenna system (FAS), which may cause unbearable rate loss to weak users, we propose to maximize the minimal rate of the system to ensure fairness. The max-min optimization problem is formulated by jointly optimizing the positions of FAs with meeting the minimum distance requirements of FAs, maximum transmitting power limit, and feasible antenna region constraints. To solve this problem, we propose an alternating algorithm with utilizing the successive convex approximation (SCA) method. Simulation results demonstrate that the proposed method significantly outperforms conventional methods in terms of maximizing the minimal achievable rate across different signal-to-noise ratios (SNRs) and normalized region sizes.

eess.SP↗

arXiv2025

Spin Chain Integrability as a Supersymmetric Gauge Duality

We establish a novel correspondence between 4D $\mathcal N=1$ supersymmetric gauge theories on $D^2\times T^2$ and open XYZ spin chains with generalized boundary conditions, extending beyond previous 3D Bethe/gauge duality frameworks. Our primary contribution is the rigorous construction of the first exact duality between 4D BCD-type gauge theories and general-boundary XYZ spin chains governed by elliptic $R$-matrices. This framework provides a universal mechanism for resolving supersymmetric gauge theory/spin-chain duality across dimensional hierarchies: 2D $\mathcal{N}=(2,2)$ $\longleftrightarrow$ XXX spin chain, 3D $\mathcal{N}=2$ $\longleftrightarrow$ XXZ spin chain, 4D $\mathcal{N}=1$ $\longleftrightarrow$ XYZ spin chain, mediated through the $Ω$-deformation parameter $ε$.

hep-th↗

arXiv2025

New tissue engineered scaffolds for rotator cuff tendon-bone interface regeneration

Healing of Tendon-bone interface(TBI) injuries is slow and is often repaired with scar tissue formation that compromises normal function. Despite the increasing maturity of surgical techniques, re-tearing of the rotator cuff after surgery remains common. The main reason for this issue is that the original structure of the rotator cuff at the TBI area is difficult to fully restore after surgery, and anatomical healing of the rotator cuff TBI is challenging to achieve solely through surgery. With the advancement of tissue engineering technology, more and more basic researchers and clinical surgeons are recognizing the enormous potential of tissue engineering in promoting TBI healing. Growing research evidence indicates that tissue engineering technology not only effectively promotes repairing and remodeling of the TBI but also reduces the formation of fibrous vascular scar tissue, leading to more orderly tissue reconstruction. The core of tissue engineering technology approaches lies in combining the use of various scaffolds, cells and bioactive molecules to simulate the natural environment of TBI healing, achieving optimal therapeutic outcomes. In this review, we will systematically summarize and highlight recent progress in the application of tissue engineering on TBI regeneration, particularly focusing on advancements in novel scaffolds and their role and potential in promoting healing of the TBI of rotator cuff, providing valuable references for clinical application and research.

q-bio.TO↗

arXiv2025

Immunological mechanisms and immunoregulatory strategies in intervertebral disc degeneration

Intervertebral discs are avascular and maintain immune privilege. However, during intervertebral disc degeneration (IDD), this barrier is disrupted, leading to extensive immune cell infiltration and localized inflammation. In degenerated discs, macrophages, T lymphocytes, neutrophils, and granulocytic myeloid-derived suppressor cells (G-MDSCs) are key players, exhibiting functional heterogeneity. Dysregulated activation of inflammatory pathways, including nuclear factor kappa-B (NF-kappaB), interleukin-17 (IL-17), and nucleotide-binding oligomerization domain-like receptor protein 3 (NLRP3) inflammasome activation, drives local pro-inflammatory responses, leading to cell apoptosis and extracellular matrix (ECM) degradation. Innovative immunotherapies, including exosome-based treatments, CRISPR/Cas9-mediated gene editing, and chemokine-loaded hydrogel systems, have shown promise in reshaping the immunological niche of intervertebral discs. These strategies can modulate dysregulated immune responses and create a supportive environment for tissue regeneration. However, current studies have not fully elucidated the mechanisms of inflammatory memory and the immunometabolic axis, and they face challenges in balancing tissue regeneration with immune homeostasis. Future studies should employ interdisciplinary approaches such as single-cell and spatial transcriptomics to map a comprehensive immune atlas of IDD, elucidate intercellular crosstalk and signaling networks, and develop integrated therapies combining targeted immunomodulation with regenerative engineering, thereby facilitating the clinical translation of effective IDD treatments.

q-bio.BM↗

arXiv2025

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling out-of-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference with dynamic thresholds. TACLR offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial deployment. Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Further, it has been successfully deployed on the real-world e-commerce platform Xianyu, processing millions of product listings daily with frequently updated, large-scale attribute taxonomies. We release the code to facilitate reproducibility and future research at https://github.com/SuYindu/TACLR.

cs.CL↗