Picture for Zhiqiang Ma

Zhiqiang Ma

"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs

Add code
Oct 20, 2024
Figure 1 for "What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
Figure 2 for "What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
Figure 3 for "What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
Figure 4 for "What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
Viaarxiv icon

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation

Add code
Oct 03, 2024
Viaarxiv icon

BuDDIE: A Business Document Dataset for Multi-task Information Extraction

Add code
Apr 05, 2024
Viaarxiv icon

TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing

Add code
Feb 07, 2024
Viaarxiv icon

DocGraphLM: Documental Graph Language Model for Information Extraction

Add code
Jan 05, 2024
Viaarxiv icon

DocLLM: A layout-aware generative language model for multimodal document understanding

Add code
Dec 31, 2023
Viaarxiv icon

Learning from Imperfect Demonstrations through Dynamics Evaluation

Add code
Dec 18, 2023
Figure 1 for Learning from Imperfect Demonstrations through Dynamics Evaluation
Figure 2 for Learning from Imperfect Demonstrations through Dynamics Evaluation
Figure 3 for Learning from Imperfect Demonstrations through Dynamics Evaluation
Figure 4 for Learning from Imperfect Demonstrations through Dynamics Evaluation
Viaarxiv icon

Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams

Add code
Oct 12, 2023
Viaarxiv icon

Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation

Add code
Jun 27, 2023
Viaarxiv icon

Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving

Add code
Jun 05, 2023
Viaarxiv icon