WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences

Xiao Liu, Hanyu Lai, Hao Yu, Yifan Xu, Aohan Zeng +4 more
6/13/2023
cs.CLcs.AI

Official code: THUDM/WebGLM (1,601 stars, Apache-2.0, last commit 2025-03-25).

Abstract

We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM). Its goal is to augment a pre-trained large language model (LLM) with web search and retrieval capabilities while being efficient for real-world deployments. To achieve this, we develop WebGLM with strategies for the LLM-augmented retriever, bootstrapped generator, and human preference-aware scorer. Specifically, we identify and address the limitations of WebGPT (OpenAI), through which WebGLM is enabled with accuracy, efficiency, and cost-effectiveness advantages. In addition, we propose systematic criteria for evaluating web-enhanced QA systems. We conduct multi-dimensional human evaluation and quantitative ablation studies, which suggest the outperformance of the proposed WebGLM designs over existing systems. WebGLM with the 10-billion-parameter GLM (10B) is shown to perform better than the similar-sized WebGPT (13B) and even comparably to WebGPT (175B) in human evaluation. The code, demo, and data are at \url{https://github.com/THUDM/WebGLM}.

View on arXivView PDF

Code Implementations(1)

THUDM/WebGLMOfficial100%
Apache-2.0

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

1,601131Shell, PythonMay 28, 20231 years agoApache-2.0
chatgptllmrlhfwebglm

Similar Papers

RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models

85% match1 repo542023

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

84% match2026

Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

84% match2026

WebCPM: Interactive Web Search for Chinese Long-form Question Answering

84% match1 repo9112023

CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering

84% match1 repo62023

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

84% match1 repo3982023

Cite this paper

@article{liu2023webglm,
  title  = {WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences},
  author = {Xiao Liu and Hanyu Lai and Hao Yu and Yifan Xu and Aohan Zeng and Zhengxiao Du and Peng Zhang and Yuxiao Dong and Jie Tang},
  year   = {2023},
  eprint = {2306.07906},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.07906v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.07906.svg)](https://codeofpaper.com/paper/2306.07906)

Discussion