arXiv subjects

Xuanhua Shi

Publications and source records attributed to Xuanhua Shi.

At least 19 recordsLinked to original sources

arXiv2026

Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference

As large language models are increasingly deployed to simulate diverse human characters, ensuring persona fidelity, defined as the extent to which an agent's behavior consistently reflects the psychological and stylistic characteristics of a target persona, has become a critical requirement. However, existing evaluation paradigms primarily rely on either holistic LLM-based judges, which are prone to "holistic appraisal hallucination'', or static psychometric inventories, which fail to capture the context-dependent fidelity required in dynamic dialogue. To address these limitations, we propose PRISM (Persona Reasoning with Inverse SFL-based Modeling), a psycholinguistically grounded framework that reformulates persona fidelity evaluation as a structured inverse inference task. Inspired by Systemic Functional Linguistics (SFL), PRISM decomposes persona fidelity into three functional dimensions: Task Framing, Interpersonal Stance, and Linguistic Style. It estimates dimension-specific evidence over a persona-conditioned label space and aggregates these signals into an interpretable and auditable evaluation process. Experiments show that PRISM yields more accurate and stable judgements than traditional holistic judging, providing a more reliable framework for persona fidelity evaluation.

cs.CL↗

arXiv2026

Figma2Code: Automating Multimodal Design to Code in the Wild

Front-end development constitutes a substantial portion of software engineering, yet converting design mockups into production-ready User Interface (UI) code remains tedious and costly. While recent work has explored automating this process with Multimodal Large Language Models (MLLMs), existing approaches typically rely solely on design images. As a result, they must infer complex UI details from images alone, often leading to degraded results. In real-world development workflows, however, design mockups are usually delivered as Figma files, a widely used tool for front-end design, that embed rich multimodal information (e.g., metadata and assets) essential for generating high-quality UI. To bridge this gap, we introduce Figma2Code, a new task that advances design-to-code into a multimodal setting and aims to automate design-to-code in the wild. Specifically, we collect paired design images and their corresponding metadata files from the Figma community. We then apply a series of processing operations, including rule-based filtering, human- and MLLM-based annotation and screening, and metadata refinement. This process yields 3,055 samples, from which designers curate a balanced dataset of 213 high-quality cases. Using this dataset, we benchmark ten state-of-the-art open-source and proprietary MLLMs. Our results show that while proprietary models achieve superior visual fidelity, they remain limited in layout responsiveness and code maintainability. Further experiments across modalities and ablation studies corroborate this limitation, partly due to models' tendency to directly map primitive visual attributes from Figma metadata.

cs.SE↗

arXiv2026

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models

Theory of Mind (ToM), the ability to attribute mental states to others, is a hallmark of social intelligence. While large language models (LLMs) demonstrate promising performance on standard ToM benchmarks, we observe that they often fail to generalize to complex task-specific scenarios, relying heavily on prompt scaffolding to mimic reasoning. The critical misalignment between the internal knowledge and external behavior raises a fundamental question: Do LLMs truly possess intrinsic cognition, and can they externalize this internal knowledge into stable, high-quality behaviors? To answer this, we introduce CoSToM (Causal-oriented Steering for ToM alignment), a framework that transitions from mechanistic interpretation to active intervention. First, we employ causal tracing to map the internal distribution of ToM features, empirically uncovering the internal layers' characteristics in encoding fundamental ToM semantics. Building on this insight, we implement a lightweight alignment framework via targeted activation steering within these ToM-critical layers. Experiments demonstrate that CoSToM significantly enhances human-like social reasoning capabilities and downstream dialogue quality.

cs.CL↗

arXiv2026

code_transformed: The Influence of Large Language Models on Code

Coding remains one of the most fundamental modes of interaction between humans and machines. With the rapid advancement of Large Language Models (LLMs), code generation capabilities have begun to significantly reshape programming practices. This development prompts a central question: Have LLMs transformed code style, and how can such transformation be characterized? In this paper, we present a pioneering study that investigates the impact of LLMs on code style, with a focus on naming conventions, complexity, maintainability, and similarity. By analyzing code from over 20,000 GitHub repositories linked to arXiv papers published between 2020 and 2025, we identify measurable trends in the evolution of coding style that align with characteristics of LLM-generated code. For instance, the proportion of snake_case function names in Python code increased from 40.7% in Q1 2023 to 49.8% in Q3 2025. Furthermore, we investigate how LLMs approach algorithmic problems by examining their reasoning processes. Our experimental results may provide the first large-scale empirical evidence that LLMs affect real-world programming style. We release all the experimental dataset and source code at: https://github.com/ignorancex/LLM_code

cs.CL↗

arXiv2025

Redox: Improving I/O Efficiency of Model Training Through File Redirection

This paper proposes Redox, a training data management system designed to achieve high I/O efficiency. The key insight is a new observation of file redirection: for model training, when training data in one file is requested, the system has the flexibility to return the data of another file. Based on this property, Redox starts with a bold design principle that chunks of data files are always read from disk in batch, and once loaded, all files in the chunk will be consumed without being loaded again. We propose efficient local and distributed file read protocol based on this principle that both minimizes the wasted data read and enables opportunistic prefetch from remote node. Moreover, we analyze file redirection's impact on randomness, and show that it has little effects on training efficiency. Experimental results indicate that Redox significantly accelerates data fetching in training, achieving up to a 4.57x improvement in end-to-end training compared to PyTorch.

cs.DC↗

arXiv2025

RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems

Large Language models are revolutionizing the conversational recommender systems through their impressive capabilities in instruction comprehension, reasoning, and human interaction. A core factor underlying effective recommendation dialogue is the ability to infer and reason about users' mental states (such as desire, intention, and belief), a cognitive capacity commonly referred to as Theory of Mind. Despite growing interest in evaluating ToM in LLMs, current benchmarks predominantly rely on synthetic narratives inspired by Sally-Anne test, which emphasize physical perception and fail to capture the complexity of mental state inference in realistic conversational settings. Moreover, existing benchmarks often overlook a critical component of human ToM: behavioral prediction, the ability to use inferred mental states to guide strategic decision-making and select appropriate conversational actions for future interactions. To better align LLM-based ToM evaluation with human-like social reasoning, we propose RecToM, a novel benchmark for evaluating ToM abilities in recommendation dialogues. RecToM focuses on two complementary dimensions: Cognitive Inference and Behavioral Prediction. The former focus on understanding what has been communicated by inferring the underlying mental states. The latter emphasizes what should be done next, evaluating whether LLMs can leverage these inferred mental states to predict, select, and assess appropriate dialogue strategies. Extensive experiments on state-of-the-art LLMs demonstrate that RecToM poses a significant challenge. While the models exhibit partial competence in recognizing mental states, they struggle to maintain coherent, strategic ToM reasoning throughout dynamic recommendation dialogues, particularly in tracking evolving intentions and aligning conversational strategies with inferred mental states.

cs.AI↗

arXiv2025

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted. To address this issue, several approaches, including training data de-duplication and differential privacy augmentation, have been proposed. However, these methods require full-model retraining for deployed CLMs, which incurs substantial computational costs. In this paper, we aim to answer the following research question: Can sensitive information memorized by CLMs be erased effectively and efficiently? We conduct a pioneering investigation into erasing sensitive memorization in CLMs through machine unlearning - a post-hoc modification method that removes specific information from trained models without requiring full retraining. Specifically, we first quantify the memorization risks of sensitive data within CLM training datasets and curate a high-risk dataset of 50,000 sensitive memorized samples as unlearning targets. We study two widely used gradient ascent-based unlearning approaches: the vanilla and constraint-based methods, and introduce CodeEraser, an advanced variant that selectively unlearns sensitive memorized segments in code while preserving the structural integrity and functional correctness of the surrounding code. Extensive experiments on three families of CLMs, i.e., CodeParrot, CodeGen-Mono, and Qwen2.5-Coder, validate the effectiveness and efficiency of CodeEraser in erasing targeted sensitive memorization while maintaining model utility.

cs.SE↗

arXiv2025

LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and functional implementation. While recent Multimodal Large Language Models (MLLMs) have shown significant potential in design-to-code tasks, they often fail to accurately preserve the layout during code generation. To this end, we draw inspiration from the Chain-of-Thought (CoT) reasoning in human cognition and propose LaTCoder, a novel approach that enhances layout preservation in webpage design during code generation with Layout-as-Thought (LaT). Specifically, we first introduce a simple yet efficient algorithm to divide the webpage design into image blocks. Next, we prompt MLLMs using a CoTbased approach to generate code for each block. Finally, we apply two assembly strategies-absolute positioning and an MLLM-based method-followed by dynamic selection to determine the optimal output. We evaluate the effectiveness of LaTCoder using multiple backbone MLLMs (i.e., DeepSeek-VL2, Gemini, and GPT-4o) on both a public benchmark and a newly introduced, more challenging benchmark (CC-HARD) that features complex layouts. The experimental results on automatic metrics demonstrate significant improvements. Specifically, TreeBLEU scores increased by 66.67% and MAE decreased by 38% when using DeepSeek-VL2, compared to direct prompting. Moreover, the human preference evaluation results indicate that annotators favor the webpages generated by LaTCoder in over 60% of cases, providing strong evidence of the effectiveness of our method.

cs.SE↗

arXiv2025

CFP: Efficient Optimization of Intra-Operator Parallelism Plans for Large Model Training

Optimizing the parallel training of large models requires exploring intra-operator parallelism plans for a computation graph that typically contains tens of thousands of primitive operators. While the optimization of parallel data processing graphs has been extensively researched in database systems, the vast search space makes it challenging to apply traditional database query optimization methods and algorithms. This paper introduces CFP, an optimization system for intra-operator parallelism that significantly reduces the complexity of searching for parallelism plans by leveraging two structural patterns found in large models. First, we identify parallel-preserving subgraphs, which ensure that the optimal global plan assigns the same parallel strategy to all operators within the subgraph. This approach allows us to avoid enumerating all possible combinations of parallel strategies for these operators. Second, we recognize repetitive subgraph patterns within the large computational graph, enabling us to profile a moderate number of representative subgraphs and accurately estimate the cost of parallelism plans with low overhead. With the significantly reduced search space, we can employ dynamic programming to search for the optimized parallelism plan. In our experiments, we demonstrate that CFP achieves significant speedups compared to the state-of-the-art framework for large models like GPT and LLAMA.

cs.DC↗

arXiv2025

CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs. This limitation, stemming from static pre-training datasets, often results in non-executable code or implementations with suboptimal safety and efficiency. To this end, this paper introduces CODESYNC, a data engine for identifying outdated code patterns and collecting real-time code knowledge updates from Python third-party libraries. Building upon CODESYNC, we develop CODESYNCBENCH, a comprehensive benchmark for assessing LLMs' ability to stay synchronized with code evolution, which covers real-world updates for 220 APIs from six Python libraries. Our benchmark offers 3,300 test cases across three evaluation tasks and an update-aware instruction tuning dataset consisting of 2,200 training samples. Extensive experiments on 14 state-of-the-art LLMs reveal that they struggle with dynamic code evolution, even with the support of advanced knowledge updating methods (e.g., DPO, ORPO, and SimPO). We believe that our benchmark can offer a strong foundation for the development of more effective methods for real-time code knowledge updating in the future. The experimental code and dataset are publicly available at: https://github.com/Lucky-voyage/Code-Sync.

cs.CL↗

arXiv2025

DawnPiper: A Memory-scablable Pipeline Parallel Training Framework

Pipeline parallelism is a crucial paradigm for large-scale model training. However, imbalances in memory footprint across stages can lead to significant GPU memory wastage, limiting the model sizes that pipeline parallelism can effectively support. In this paper, we introduce DawnPiper, a memory-scalable pipeline parallel training framework. Firstly, we develop a DL compilation-based profiling method that transforms the model into a fine-grained computation graph. This refinement gives us a finer granularity of model partitioning and memory optimization while facilitating automatic code generation. Based on observed memory usage characteristics, we derive a performance-optimal theorem for pipeline parallel partitioning that substantially reduces the partition search space. Secondly, we propose a binary pipeline partitioning algorithm and utilize a cost-model based memory optimization approach to efficiently identify nearly optimal pipeline parallel strategy. DawnPiper achieves up to a 4x and 11x increase in trainable maximum batch size compared to vPipe and PipeDream, respectively, and provides up to a 1.5x performance speedup compared to vPipe.

cs.DC↗

arXiv2024

gECC: A GPU-based high-throughput framework for Elliptic Curve Cryptography

Elliptic Curve Cryptography (ECC) is an encryption method that provides security comparable to traditional techniques like Rivest-Shamir-Adleman (RSA) but with lower computational complexity and smaller key sizes, making it a competitive option for applications such as blockchain, secure multi-party computation, and database security. However, the throughput of ECC is still hindered by the significant performance overhead associated with elliptic curve (EC) operations. This paper presents gECC, a versatile framework for ECC optimized for GPU architectures, specifically engineered to achieve high-throughput performance in EC operations. gECC incorporates batch-based execution of EC operations and microarchitecture-level optimization of modular arithmetic. It employs Montgomery's trick to enable batch EC computation and incorporates novel computation parallelization and memory management techniques to maximize the computation parallelism and minimize the access overhead of GPU global memory. Also, we analyze the primary bottleneck in modular multiplication by investigating how the user codes of modular multiplication are compiled into hardware instructions and what these instructions' issuance rates are. We identify that the efficiency of modular multiplication is highly dependent on the number of Integer Multiply-Add (IMAD) instructions. To eliminate this bottleneck, we propose techniques to minimize the number of IMAD instructions by leveraging predicate registers to pass the carry information and using addition and subtraction instructions (IADD3) to replace IMAD instructions. Our results show that, for ECDSA and ECDH, gECC can achieve performance improvements of 5.56x and 4.94x, respectively, compared to the state-of-the-art GPU-based system. In a real-world blockchain application, we can achieve performance improvements of 1.56x, compared to the state-of-the-art CPU-based system.

cs.CR↗

arXiv2024

Hyperbolic Hypergraph Neural Networks for Multi-Relational Knowledge Hypergraph Representation

Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks.

cs.LG↗

arXiv2024

Can Large Language Models Serve as Evaluators for Code Summarization?

Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and difficult to scale. Commonly used automatic metrics, such as BLEU, ROUGE-L, METEOR, and BERTScore, often fail to align closely with human judgments. In this paper, we explore the potential of Large Language Models (LLMs) for evaluating code summarization. We propose CODERPE (Role-Player for Code Summarization Evaluation), a novel method that leverages role-player prompting to assess the quality of generated summaries. Specifically, we prompt an LLM agent to play diverse roles, such as code reviewer, code author, code editor, and system analyst. Each role evaluates the quality of code summaries across key dimensions, including coherence, consistency, fluency, and relevance. We further explore the robustness of LLMs as evaluators by employing various prompting strategies, including chain-of-thought reasoning, in-context learning, and tailored rating form designs. The results demonstrate that LLMs serve as effective evaluators for code summarization methods. Notably, our LLM-based evaluator, CODERPE , achieves an 81.59% Spearman correlation with human evaluations, outperforming the existing BERTScore metric by 17.27%.

cs.SE↗

arXiv2024

CANDY: A Benchmark for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion

Approximate K Nearest Neighbor (AKNN) algorithms play a pivotal role in various AI applications, including information retrieval, computer vision, and natural language processing. Although numerous AKNN algorithms and benchmarks have been developed recently to evaluate their effectiveness, the dynamic nature of real-world data presents significant challenges that existing benchmarks fail to address. Traditional benchmarks primarily assess retrieval effectiveness in static contexts and often overlook update efficiency, which is crucial for handling continuous data ingestion. This limitation results in an incomplete assessment of an AKNN algorithms ability to adapt to changing data patterns, thereby restricting insights into their performance in dynamic environments. To address these gaps, we introduce CANDY, a benchmark tailored for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion. CANDY comprehensively assesses a wide range of AKNN algorithms, integrating advanced optimizations such as machine learning-driven inference to supplant traditional heuristic scans, and improved distance computation methods to reduce computational overhead. Our extensive evaluations across diverse datasets demonstrate that simpler AKNN baselines often surpass more complex alternatives in terms of recall and latency. These findings challenge established beliefs about the necessity of algorithmic complexity for high performance. Furthermore, our results underscore existing challenges and illuminate future research opportunities. We have made the datasets and implementation methods available at: https://github.com/intellistream/candy.

cs.DB↗

arXiv2024

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project's context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate CoCoGen with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines.

cs.CL↗

arXiv2024

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness.

cs.CR↗

arXiv2024

Graph for Science: From API based Programming to Graph Engine based Programming for HPC

Modern scientific applications predominantly run on large-scale computing platforms, necessitating collaboration between scientific domain experts and high-performance computing (HPC) experts. While domain experts are often skilled in customizing domain-specific scientific computing routines, which often involves various matrix computations, HPC experts are essential for achieving efficient execution of these computations on large-scale platforms. This process often involves utilizing complex parallel computing libraries tailored to specific matrix computation scenarios. However, the intricate programming procedure and the need for deep understanding in both application domains and HPC poses significant challenges to the widespread adoption of scientific computing. In this research, we observe that matrix computations can be transformed into equivalent graph representations, and that by utilizing graph processing engines, HPC experts can be freed from the burden of implementing efficient scientific computations. Based on this observation, we introduce a graph engine-based scientific computing (Graph for Science) paradigm, which provides a unified graph programming interface, enabling domain experts to promptly implement various types of matrix computations. The proposed paradigm leverages the underlying graph processing engine to achieve efficient execution, eliminating the needs for HPC expertise in programming large-scale scientific applications. Our results show that the graph engine-based scientific computing paradigm achieves performance comparable to the best-performing implementations based on existing parallel computing libraries and bespoke implementations. Importantly, the paradigm greatly simplifies the development of scientific computations on large-scale platforms, reducing the programming difficulty for scientists and facilitating broader adoption of scientific computing.

cs.DC↗