arXiv subjects

Kaiwen He

Publications and source records attributed to Kaiwen He.

8 recordsLinked to original sources

arXiv2026

FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information

Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Reporting Language) provides a standard for tagging financial figures, mapping thousands of facts to over 10k US GAAP concepts remains costly and error prone. Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents. Consequently, these benchmarks fail to evaluate Large Language Models (LLMs) under realistic reporting conditions. To bridge this gap, we introduce FinTagging, the first comprehensive benchmark for structure aware and full scope XBRL tagging. We decompose the complex tagging process into two subtasks: (1) FinNI (Financial Numeric Identification), which extracts entities and types from heterogeneous contexts including text and tables; and (2) FinCL (Financial Concept Linking), which maps extracted entities to the full US GAAP taxonomy. This two stage formulation enables a fair assessment of LLMs' capabilities in numerical reasoning and taxonomy alignment. Evaluating diverse LLMs in zero shot settings reveals that while models generalize well in extraction, they struggle significantly with fine grained concept linking, highlighting critical limitations in domain specific structure aware reasoning.

cs.CL↗

arXiv2026

Evaluation and Benchmarking Suite for Financial Large Language Models and Agents

Over the past three years, the financial services industry has witnessed Large Language Models (LLMs) and agents transitioning from the exploration stage to readiness and governance stages. Financial large language models (FinLLMs), such as open FinGPT and proprietary BloombergGPT , have great potential in financial applications, including retrieving real-time data, tutoring, analyzing sentiment of social media, analyzing SEC filings, and agentic trading. However, general-purpose LLMs and agents lack financial expertise and often struggle to handle complex financial reasoning. This paper presents an evaluation and benchmarking suite that covers the lifecycle of FinLLMs and FinAgents. This suite led by SecureFinAI Lab includes an evaluation pipeline and a governance framework collaborating with Linux Foundation and PyTorch Foundation, a FinLLM Leaderboard with HuggingFace, an AgentOps framework with Red Hat, and a documentation website with Rensselear Center of Open Source. Our collaborative development evolves through three stages: FinLLM Exploration (2023), FinLLM Readiness (2024), and FinAI Governance (2025). The proposed suite serves as an open platform that enables researchers and practitioners to perform both quantitative and qualitative analysis of different FinLLMs and FinAgents, fostering a more robust and reliable FinAI ecosystem.

cs.CE↗

arXiv2025

Reasoning Models Ace the CFA Exams

Previous research has reported that large language models (LLMs) demonstrate poor performance on the Chartered Financial Analyst (CFA) exams. However, recent reasoning models have achieved strong results on graduate-level academic and professional examinations across various disciplines. In this paper, we evaluate state-of-the-art reasoning models on a set of mock CFA exams consisting of 980 questions across three Level I exams, two Level II exams, and three Level III exams. Using the same pass/fail criteria from prior studies, we find that most models clear all three levels. The models that pass, ordered by overall performance, are Gemini 3.0 Pro, Gemini 2.5 Pro, GPT-5, Grok 4, Claude Opus 4.1, and DeepSeek-V3.1. Specifically, Gemini 3.0 Pro achieves a record score of 97.6% on Level I. Performance is also strong on Level II, led by GPT-5 at 94.3%. On Level III, Gemini 2.5 Pro attains the highest score with 86.4% on multiple-choice questions while Gemini 3.0 Pro achieves 92.0% on constructed-response questions.

cs.AI↗

arXiv2025

Structure-Aware Spectral Sparsification via Uniform Edge Sampling

Spectral clustering is a fundamental method for graph partitioning, but its reliance on eigenvector computation limits scalability to massive graphs. Classical sparsification methods preserve spectral properties by sampling edges proportionally to their effective resistances, but require expensive preprocessing to estimate these resistances. We study whether uniform edge sampling-a simple, structure-agnostic strategy-can suffice for spectral clustering. Our main result shows that for graphs admitting a well-separated $k$-clustering, characterized by a large structure ratio $Υ(k) = λ_{k+1} / ρ_G(k)$, uniform sampling preserves the spectral subspace used for clustering. Specifically, we prove that uniformly sampling $O(γ^2 n \log n / ε^2)$ edges, where $γ$ is the Laplacian condition number, yields a sparsifier whose top $(n-k)$-dimensional eigenspace is approximately orthogonal to the cluster indicators. This ensures that the spectral embedding remains faithful, and clustering quality is preserved. Our analysis introduces new resistance bounds for intra-cluster edges, a rank-$(n-k)$ effective resistance formulation, and a matrix Chernoff bound adapted to the dominant eigenspace. These tools allow us to bypass importance sampling entirely. Conceptually, our result connects recent coreset-based clustering theory to spectral sparsification, showing that under strong clusterability, even uniform sampling is structure-aware. This provides the first provable guarantee that uniform edge sampling suffices for structure-preserving spectral clustering.

cs.LG↗

arXiv2025

Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution

Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from disordered action sequencing and excessive trial and error during execution. This paper introduces Recon-Act, a self-evolving multi-agent framework grounded in Reconnaissance-Action behavioral paradigm. The system comprises a Reconnaissance Team and an Action Team: the former conducts comparative analysis and tool generation, while the latter handles intent decomposition, tool orchestration, and execution. By contrasting the erroneous trajectories with successful ones, the Reconnaissance Team infers remedies, and abstracts them into a unified notion of generalized tools, either expressed as hints or as rule-based codes, and register to the tool archive in real time. The Action Team reinference the process empowered with these targeting tools, thus establishing a closed-loop training pipeline of data-tools-action-feedback. Following the 6 level implementation roadmap proposed in this work, we have currently reached Level 3 (with limited human-in-the-loop intervention). Leveraging generalized tools obtained through reconnaissance, Recon-Act substantially improves adaptability to unseen websites and solvability on long-horizon tasks, and achieves state-of-the-art performance on the challenging VisualWebArena dataset.

cs.AI↗

arXiv2025

Preconditioning via Randomized Range Deflation (RandRAND)

We introduce RandRAND, a new class of randomized preconditioning methods for large-scale linear systems. RandRAND deflates the spectrum via efficient orthogonal projections onto random subspaces, without computing eigenpairs or low-rank approximations. This leads to advantages in computational cost and numerical stability. We establish rigorous condition number bounds that depend only weakly on the problem size and that reduce to a small constant when the dimension of the deflated subspace is comparable to the effective spectral dimension. RandRAND can be employed without explicit operations with the deflation basis, enabling the effective use of fast randomized transforms. In this setting, the costly explicit basis orthogonalization is bypassed by using fast randomized Q-less QR factorizations or iterative methods for computing orthogonal projections. These strategies balance the cost of constructing RandRAND preconditioners and applying them within linear solvers, and can ensure robustness to rounding errors.

math.NA↗

arXiv2020

Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework

Internet of Things (IoT) have widely penetrated in different aspects of modern life and many intelligent IoT services and applications are emerging. Recently, federated learning is proposed to train a globally shared model by exploiting a massive amount of user-generated data samples on IoT devices while preventing data leakage. However, the device, statistical and model heterogeneities inherent in the complex IoT environments pose great challenges to traditional federated learning, making it unsuitable to be directly deployed. In this article we advocate a personalized federated learning framework in a cloud-edge architecture for intelligent IoT applications. To cope with the heterogeneity issues in IoT environments, we investigate emerging personalized federated learning methods which are able to mitigate the negative effects caused by heterogeneity in different aspects. With the power of edge computing, the requirements for fast-processing capacity and low latency in intelligent IoT applications can also be achieved. We finally provide a case study of IoT based human activity recognition to demonstrate the effectiveness of personalized federated learning for intelligent IoT applications.

cs.NI↗

arXiv2020

DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network

Online social networks (OSNs) are emerging as the most popular mainstream platform for content cascade diffusion. In order to provide satisfactory quality of experience (QoE) for users in OSNs, much research dedicates to proactive content placement by using the propagation pattern, user's personal profiles and social relationships in open social network scenarios (e.g., Twitter and Weibo). In this paper, we take a new direction of popularity-aware content placement in a closed social network (e.g., WeChat Moment) where user's privacy is highly enhanced. We propose a novel data-driven holistic deep learning framework, namely DeepCP, for joint diffusion-aware cascade prediction and autonomous content placement without utilizing users' personal and social information. We first devise a time-window LSTM model for content popularity prediction and cascade geo-distribution estimation. Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users' QoE. We conduct extensive experiments using cascade diffusion traces in WeChat Moment (WM). Evaluation results corroborate that the proposed DeepCP framework can predict the content popularity with a high accuracy, generate efficient placement decision in a real-time manner, and achieve significant content access latency reduction over existing schemes.

cs.SI↗