arXiv subjects

Zhanli Li

Publications and source records attributed to Zhanli Li.

5 recordsLinked to original sources

arXiv2026

Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA

This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark for multi-document analytical QA, where questions require extracting and synthesizing information across numerous documents to perform quantitative analysis. Unlike existing multi-document QA benchmarks that typically require information from only a few documents with limited cross-document reasoning, MuDABench demands extensive inter-document analysis and aggregation. Constructed via distant supervision by leveraging document-level metadata and annotated financial databases, MuDABench comprises over 80,000 pages and 332 analytical QA instances. We also propose an evaluation protocol that measures final answer accuracy and uses intermediate-fact coverage as an auxiliary diagnostic signal for the reasoning process. Experiments reveal that standard RAG systems, which treat all documents as a flat retrieval pool, perform poorly. To address these limitations, we propose a multi-agent workflow that orchestrates planning, extraction, and code generation modules. While this approach substantially improves both process and outcome metrics, a significant gap remains compared to human expert performance. Our analysis identifies two primary bottlenecks: single-document information extraction accuracy and insufficient domain-specific knowledge in current systems. MuDABench is available at https://github.com/Zhanli-Li/MuDABench.

cs.CL↗

arXiv2026

DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing agentic search frameworks typically treat long documents as flat collections of unstructured chunks, disregarding the native hierarchical organization and sequential logic essential for human comprehension. To bridge this gap, we introduce \textbf{DeepRead}, a structure-aware document reasoning agent designed to operationalize document-native structural priors into actionable reasoning capabilities. Leveraging the structural fidelity of modern OCR, DeepRead constructs a paragraph-level, coordinate-based navigation system and equips the LLM with two synergistic tools: \textsf{Retrieve} for scanning-aware localization, and \textsf{ReadSection} for contiguous, order-preserving reading within specific hierarchical scopes. This design elicits a human-like ``locate-then-read'' reasoning paradigm, effectively mitigating the context fragmentation inherent in traditional retrieval methods. Extensive evaluations across four benchmarks spanning diverse document types demonstrate that DeepRead outperforms Search-o1-style agentic search baselines by an average of 10.3\%. Fine-grained behavioral analysis further confirms that DeepRead autonomously adopts human-aligned reading strategies, validating the critical role of structural awareness in achieving precise document reasoning. Our code is available at https://github.com/Zhanli-Li/DeepRead.

cs.AI↗

arXiv2025

What influenced the lack of diversity in CSR after the company's losses: evidence from topic modeling

The diversity of corporate social responsibility (CSR) disclosure is a crucial dimension of corporate transparency, reflecting the breadth and resilience of a firm's social responsibility. Using CSR reports of Chinese A-share firms from 2006 to 2023, this paper applies Latent Dirichlet Allocation (LDA) to extract topics and quantifies disclosure diversity using the Gini-Simpson index and Shannon entropy. Regression results show that corporate losses significantly compress CSR topic diversity, consistent with the slack resources hypothesis. Both external and internal governance mechanisms mitigate this effect: higher media attention, stronger executive compensation incentives, and greater supervisory board shareholding attenuate the loss-diversity penalty. Results are robust to instrumental variables estimation, propensity score matching, and placebo tests. Heterogeneity analyses indicate weaker effects in firms with third-party assurance, those disclosing work safety content, large firms, and those in less competitive industries. Our study highlights the structural impact of financial distress on non-financial disclosure and provides practical implications for optimizing CSR communication, refining evaluation frameworks for rating agencies, and designing diversified disclosure standards.

econ.GN↗

arXiv2025

ESG Rating Disagreement and Corporate Total Factor Productivity:Inference and Prediction

This paper examines how ESG rating disagreement (Dis) affects corporate total factor productivity (TFP) in China based on data of A-share listed companies from 2015 to 2022. We find that Dis reduces TFP, especially in state-owned, non-capital-intensive, low-pollution and high-tech firms, green innovation strengthens the dampening effect of Dis on TFP, and that Dis lowers corporate TFP by increasing financing constraints and weakening human capital. Furthermore, XGBoost regression demonstrates that Dis plays a significant role in predicting TFP, with SHAP showing that the dampening effect of ESG rating disagreement on TFP is still pronounced in firms with large Dis values.

econ.GN↗

arXiv2018

Color Image Enhancement Method Based on Weighted Image Guided Filtering

A novel color image enhancement method is proposed based on Retinex to enhance color images under non-uniform illumination or poor visibility conditions. Different from the conventional Retinex algorithms, the Weighted Guided Image Filter is used as a surround function instead of the Gaussian filter to estimate the background illumination, which can overcome the drawbacks of local blur and halo artifact that may appear by Gaussian filter. To avoid color distortion, the image is converted to the HSI color model, and only the intensity channel is enhanced. Then a linear color restoration algorithm is adopted to convert the enhanced intensity image back to the RGB color model, which ensures the hue is constant and undistorted. Experimental results show that the proposed method is effective to enhance both color and gray images with low exposure and non-uniform illumination, resulting in better visual quality than traditional method. At the same time, the objective evaluation indicators are also superior to the conventional methods. In addition, the efficiency of the proposed method is also improved thanks to the linear color restoration algorithm.

cs.CV↗