Haoran Zheng

Haoran Zheng

Auto-generated profile, based on publicly available information

Haoran Zheng


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
HZHaoran Zheng
Haoran Zheng
CCChiaHua Chang
ChiaHua Chang
KLKeqin Li
Keqin Li
JHJinjin Huang
Jinjin Huang
ZYZe Yang
Ze Yang
TLTianrui Liu
Tianrui Liu
Financial research report generation is challengingdue to diverse data types, real-time requirements, and thecomplexity of financial analysis. This paper introduces FinGPT-Agent, a multi-agent framework that uses Large LanguageModels (LLMs) to tackle these challenges. The frameworkincludes multimodal fusion for handling different data types,task-specific optimization with Low-Rank Adaptation (LoRA),retrieval-augmented generation with contrastive learning forbetter context, and reinforcement learning with human feedbackto improve report quality. A hierarchical attention mechanismhelps summarize long financial documents. Experiments showthat FinGPT-Agent performs better than baseline models andsets a benchmark for financial report generation using LLMs.

30 May 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
LFLei Fu
Lei Fu
HZHaoran Zheng
Haoran Zheng
BLBeichen Liu
Beichen Liu
ZZZhejun Zhao
Zhejun Zhao
LLLipeng Liu
Lipeng Liu
XLXuan Li
Xuan Li
Detecting AI-generated text is an important challenge, especially as large language models become better at creating content that looks like human writing. This paper presents a teacher-student framework to improve the performance and efficiency of short-context document classification. The framework uses domain adaptation and data augmentation to improve detection. The teacher model combines DeBERTa-v3-large and Mamba-790m models, using their fine-tuning on domain-specific data and semantic knowledge for accurate predictions. The student model works with short-context text of 128 and 256 tokens and learns from the teacher to balance accuracy and computational efficiency. To make the model more robust, we built a data generation and augmentation pipeline, applying techniques like spelling correction, character removal, and case flipping to increase data variety. The proposed framework outperforms current methods in accuracy and robustness, offering an efficient solution for detecting AI-generated text. This work also lays the groundwork for future studies on multilingual classification and real-time inference improvements in AI text detection.