Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.

The Tensorflow implementation of "Review-driven Answer Generation for Product-related Questions in E-commerce ", WSDM 2019.

Vietnamese Legal Question Answering with Machine Reading Comprehension (MRC) and Answer Generation (AG) approches. (KSE 2024)

A Python library for generating high-quality question-answer pairs from PDF, DOCX, MD, and TXT files

Code for Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning, EMNLP 2021

Work on answering questions in digital humanities (history) using various large language models (LLMs)

Comprehensive Evaluation On Answer Calibration For Multi-Step Reasoning

ViAG: A Novel Framework for Fine-tuning Answer Generation models ultilizing Encoder-Decoder and Decoder-only Transformers's architecture

In this we generate QA pairs from the paragraph content and pdf content

ViLegalLM: Language Models for Vietnamese Legal Text (ACL Findings 2026)

This app allows users to auto-generate unlimited exam preparation questions, based off their own, or a community created question.

RAG-powered PDF chatbot built with LangChain, Mistral AI, and ChromaDB — upload any document and get context-grounded answers via a custom Streamlit UI

Open-Domain Chitchat System with Multi-Module Architecture for Enhanced Conversational AI