WebGLM: Towards An Efficient Web-enhanced Question Answering System with Human Preference

? Paper (KDD 2023) | ? Github Repo

Introduction

WebGLM aspires to provide an efficient and cost-effective web-enhanced question-answering system using the 10-billion-parameter General Language Model (GLM). It aims to improve real-world application deployment by integrating web search and retrieval capabilities into the pre-trained language model.

WebGLM is built by the following parts:

• LLM-augmented Retriever : Enhances the retrieval of relevant web content to better aid in answering questions accurately.
• Bootstrapped Generator : Generates human-like responses to questions, leveraging the power of the GLM to provide refined answers.
• Human Preference-aware Scorer : Estimates the quality of generated responses by prioritizing human preferences, ensuring the system produces useful and engaging content.

This repo is the implementation of Bootstrap Generator .

See our Github Repo for more detailed usage.