arXiv subjects

Jiyuan Shen

Publications and source records attributed to Jiyuan Shen.

10 recordsLinked to original sources

arXiv2026

Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis

Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their own methods to determine task success, such as database lookups, regex match, etc., adding complexity to the development of a unified agent evaluation approach. Moreover, they do not systematically account for the user's role nor expertise in the interaction, providing incomplete insights into the agent's performance. We argue that effective agent evaluation goes beyond correctness alone, incorporating conversation quality, efficiency and systematic diagnosis of agent errors. To address this, we introduce the TED framework (Talk, Evaluate, Diagnose). (1) Talk: We leverage reusable, generic expert and non-expert user persona templates for user-agent interaction. (2) Evaluate: We adapt existing datasets by representing subgoals-such as tool signatures, and responses-as natural language grading notes, evaluated automatically with LLM-as-a-judge. We propose new metrics that capture both turn efficiency and intermediate progress of the agent complementing the user-aware setup. (3) Diagnose: We introduce an automated error analysis tool that analyzes the inconsistencies of the judge and agents, uncovering common errors, and providing actionable feedback for agent improvement. We show that our TED framework reveals new insights regarding agent performance across models and user expertise levels. We also demonstrate potential gains in agent performance with peaks of 8-10% on our proposed metrics after incorporating the identified error remedies into the agent's design.

cs.AI↗

arXiv2026

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets

Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only pipeline--while simpler--can truly match the performance of traditional OCR+MLLM setups. In this paper, we conduct a large-scale benchmarking study that evaluates various out-of-the-box MLLMs on business-document information extraction. To examine and explore failure modes, we propose an automated hierarchical error analysis framework that leverages large language models (LLMs) to diagnose error patterns systematically. Our findings suggest that OCR may not be necessary for powerful MLLMs, as image-only input can achieve comparable performance to OCR-enhanced approaches. Moreover, we demonstrate that carefully designed schema, exemplars, and instructions can further enhance MLLMs performance. We hope this work can offer practical guidance and valuable insight for advancing document information extraction.

cs.CL↗

arXiv2025

Direct Expression for One-Loop Tensor Reduction with Lorentz Indices via Generating Function

In recent work, we derived a direct expression for one-loop tensor reduction using generating functions and Feynman parametrization in projective space, avoiding recursive relations. However, for practical applications, this expression still presents two challenges: (1) While the final reduction coefficients are expressed in terms of the dimension D and Mandelstam variables, the given expression explicitly contains irrational functions; (2) The expression involves an auxiliary vector R, which can be eliminated via differentiation $\frac{\partial}{\partial R}$, but the presence of irrational terms making differentiation cumbersome. (3) Most practical applications require the tensor form with Lorentz indices. In this paper, we provide a rational form of the reduction coefficients with Lorentz indices, free from recursion. Additionally, We provide a pure Wolfram Mathematica implementation of the code. Our practical tests demonstrate that this direct expression achieves significantly higher computational efficiency compared to the traditional Passarino-Veltman (PV) reduction or other recursion-based methods.

hep-th↗

arXiv2024

General One-loop Generating Function by IBP relations

In this paper we have studied the most general generating function of reduction for one loop integrals with arbitrary tensor structure in numerator and arbitrary power distribution of propagators in denominator. Using IBP relations, we have established the partial differential equations for these generating functions and solved them analytically. These results provide useful guidance for applying generating function method to reductions of higher loop integrals.

hep-ph↗

arXiv2024

A Survey on Federated Unlearning: Challenges, Methods, and Future Directions

In recent years, the notion of ``the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals upon their requests. Consequently, machine unlearning (MU) has gained considerable attention which allows an ML model to selectively eliminate identifiable information. Evolving from MU, federated unlearning (FU) has emerged to confront the challenge of data erasure within federated learning (FL) settings, which empowers the FL model to unlearn an FL client or identifiable information pertaining to the client. Nevertheless, the distinctive attributes of federated learning introduce specific challenges for FU techniques. These challenges necessitate a tailored design when developing FU algorithms. While various concepts and numerous federated unlearning schemes exist in this field, the unified workflow and tailored design of FU are not yet well understood. Therefore, this comprehensive survey delves into the techniques and methodologies in FU providing an overview of fundamental concepts and principles, evaluating existing federated unlearning algorithms, and reviewing optimizations tailored to federated learning. Additionally, it discusses practical applications and assesses their limitations. Finally, it outlines promising directions for future research.

cs.CR↗

arXiv2024

An Explicit Expression of Generating Function for One-Loop Tensor Reduction

This work introduces an explicit expression for the generation function for the reduction of an $n$-gon to an $(n-k)$-gon. A novel recursive relation of generation function is formulated based on Feynman Parametrization in projective space, involving a single ordinary differential equation. The explicit formulation of generation functions provides crucial insights into the complex analytic structure inherent in loop amplitudes.

hep-ph↗

arXiv2024

Privacy-Preserving Federated Unlearning with Certified Client Removal

In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client's influence from the global model in Federated Learning (FL) systems, thereby ensuring the ``right to be forgotten" (RTBF). State-of-the-art methods for unlearning use historical data from FL clients, such as gradients or locally trained models. However, studies have revealed significant information leakage in this setting, with the possibility of reconstructing a user's local data from their uploaded information. Addressing this, we propose Starfish, a privacy-preserving federated unlearning scheme using Two-Party Computation (2PC) techniques and shared historical client data between two non-colluding servers. Starfish builds upon existing FU methods to ensure privacy in unlearning processes. To enhance the efficiency of privacy-preserving FU evaluations, we suggest 2PC-friendly alternatives for certain FU algorithm operations. We also implement strategies to reduce costs associated with 2PC operations and lessen cumulative approximation errors. Moreover, we establish a theoretical bound for the difference between the unlearned global model via Starfish and a global model retrained from scratch for certified client removal. Our theoretical and experimental analyses demonstrate that Starfish achieves effective unlearning with reasonable efficiency, maintaining privacy and security in FL systems.

cs.CR↗

arXiv2024

Effective Intrusion Detection in Heterogeneous Internet-of-Things Networks via Ensemble Knowledge Distillation-based Federated Learning

With the rapid development of low-cost consumer electronics and cloud computing, Internet-of-Things (IoT) devices are widely adopted for supporting next-generation distributed systems such as smart cities and industrial control systems. IoT devices are often susceptible to cyber attacks due to their open deployment environment and limited computing capabilities for stringent security controls. Hence, Intrusion Detection Systems (IDS) have emerged as one of the effective ways of securing IoT networks by monitoring and detecting abnormal activities. However, existing IDS approaches rely on centralized servers to generate behaviour profiles and detect anomalies, causing high response time and large operational costs due to communication overhead. Besides, sharing of behaviour data in an open and distributed IoT network environment may violate on-device privacy requirements. Additionally, various IoT devices tend to capture heterogeneous data, which complicates the training of behaviour models. In this paper, we introduce Federated Learning (FL) to collaboratively train a decentralized shared model of IDS, without exposing training data to others. Furthermore, we propose an effective method called Federated Learning Ensemble Knowledge Distillation (FLEKD) to mitigate the heterogeneity problems across various clients. FLEKD enables a more flexible aggregation method than conventional model fusion techniques. Experiment results on the public dataset CICIDS2019 demonstrate that the proposed approach outperforms local training and traditional FL in terms of both speed and performance and significantly improves the system's ability to detect unknown attacks. Finally, we evaluate our proposed framework's performance in three potential real-world scenarios and show FLEKD has a clear advantage in experimental results.

cs.CR↗

arXiv2024

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model. Although various methods exist for detecting those clients in FL, identifying malicious clients requires sufficient model updates, and hence by the time malicious clients are detected, FL models have been already poisoned. Thus, a method is needed to recover an accurate global model after malicious clients are identified. Current recovery methods rely on (i) all historical information from participating FL clients and (ii) the initial model unaffected by the malicious clients, leading to a high demand for storage and computational resources. In this paper, we show that highly effective recovery can still be achieved based on (i) selective historical information rather than all historical information and (ii) a historical model that has not been significantly affected by malicious clients rather than the initial model. In this scenario, while maintaining comparable recovery performance, we can accelerate the recovery speed and decrease memory consumption. Following this concept, we introduce Crab, an efficient and certified recovery method, which relies on selective information storage and adaptive model rollback. Theoretically, we demonstrate that the difference between the global model recovered by Crab and the one recovered by train-from-scratch can be bounded under certain assumptions. Our empirical evaluation, conducted across three datasets over multiple machine learning models, and a variety of untargeted and targeted poisoning attacks reveals that Crab is both accurate and efficient, and consistently outperforms previous approaches in terms of both recovery speed and memory consumption.

cs.CR↗

arXiv2023

AST: Effective Dataset Distillation through Alignment with Smooth and High-Quality Expert Trajectories

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a very small number of highly representative and informative samples from real-world datasets. This approach, known as Dataset Distillation (DD), proposes a perspective for data-efficient learning. Despite recent progress in this field, the performance of existing methods still cannot meet expectations, and distilled datasets cannot effectively replace original datasets. In this paper, unlike previous methods that focus solely on improving the effectiveness of student distillation, we recognize and leverage the important mutual influence between expert and student models. We observed that the smoothness of expert trajectories has a significant impact on subsequent student parameter alignment. Based on this, we propose an effective DD framework named AST, standing for Alignment with Smooth and high-quality expert Trajectories. We devise the integration of clipping loss and gradient penalty to regulate the rate of parameter changes in expert trajectory generation. To further refine the student parameter alignment with expert trajectory, we put forward representative initialization for the synthetic dataset and balanced inner-loop loss in response to the sensitivity exhibited towards randomly initialized variables during distillation. We also propose two enhancement strategies, namely intermediate matching loss and weight perturbation, to mitigate the potential occurrence of cumulative errors. We conduct extensive experiments on datasets of different scales, sizes, and resolutions. The results demonstrate that the proposed method significantly outperforms prior methods.

cs.CV↗