4 papers
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham +3
We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-spe…
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
Hieu Man, Van-Cuong Pham, Nghia Trung Ngo +2
Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-styl…
AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications
Linh The Nguyen, Chi Tran, Dung Ngoc Nguyen +3
We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers…
Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective
Van-Cuong Pham, Thien Huu Nguyen
Activation Editing, which involves directly editting the internal representations of large language models (LLMs) to alter their behaviors and achieve desired properties, has emerg…