WebGLM：面向具有人类偏好的高效网络增强问答系统

摘要

我们提出了WebGLM，这是一个基于通用语言模型（GLM）的增强型问答系统，旨在增强预训练的大型语言模型（LLM）的网络搜索和检索能力，同时适用于实际部署。为实现这一目标，我们开发了WebGLM，并采用LLM增强的检索器、引导式生成器和人类偏好感知评分器等策略。具体来说，我们识别并解决了WebGPT（OpenAI）的局限性，使WebGLM在准确性、效率和成本效益方面具有优势。此外，我们提出了评估增强型网络问答系统的系统性标准。我们进行了多维人类评估和定量消融研究，结果表明所提出的WebGLM设计优于现有系统。在人类评估中，具有100亿参数GLM（10B）的WebGLM表现优于相似规模的WebGPT（13B），甚至与WebGPT（175B）相媲美。代码、演示和数据可在https://github.com/THUDM/WebGLM找到。

English

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 https://github.com/THUDM/WebGLM.

WebGLM：面向具有人类偏好的高效网络增强问答系统

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

摘要

Support