7 papers
Angular Steering: Behavior Control via Rotation in Activation Space
Hieu M. Vu, Tan M. Nguyen
Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment.…
Activation Steering with a Feedback Controller
Dung V. Nguyen, Hieu M. Vu, Nhi Y. Pham +2
Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven b…
Inferring Properties of Graph Neural Networks
Dat Nguyen, Hieu M. Vu, Cong-Thanh Le +4
We propose GNNInfer, the first automatic property inference technique for GNNs. To tackle the challenge of varying input structures in GNNs, GNNInfer first identifies a set of repr…
Improving Document Image Understanding with Reinforcement Finetuning
Bao-Sinh Nguyen, Dung Tien Le, Hieu M. Vu +3
Successful Artificial Intelligence systems often require numerous labeled data to extract information from document images. In this paper, we investigate the problem of improving t…
Jointly Learning Span Extraction and Sequence Labeling for Information Extraction from Business Documents
Nguyen Hong Son, Hieu M. Vu, Tuan-Anh D. Nguyen +1
This paper introduces a new information extraction model for business documents. Different from prior studies which only base on span extraction or sequence labeling, the model tak…
A Span Extraction Approach for Information Extraction on Visually-Rich Documents
Tuan-Anh D. Nguyen, Hieu M. Vu, Nguyen Hong Son +1
Information extraction (IE) for visually-rich documents (VRDs) has achieved SOTA performance recently thanks to the adaptation of Transformer-based language models, which shows the…
Revising FUNSD dataset for key-value detection in document images
Hieu M. Vu, Diep Thi-Ngoc Nguyen
FUNSD is one of the limited publicly available datasets for information extraction from document im-ages. The information in the FUNSD dataset is defined by text areas of four cate…