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}.

翻译：我们提出WebGLM，一种基于通用语言模型（GLM）的网络增强问答系统。其目标是在增强预训练大语言模型（LLM）的网络搜索与检索能力的同时，保持实际部署中的高效性。为实现这一目标，我们开发了WebGLM，包含LLM增强检索器、自举生成器与人类偏好感知评分器等策略。具体而言，我们识别并解决了WebGPT（OpenAI）的局限性，使WebGLM在准确性、效率与成本效益方面具有优势。此外，我们提出了评估网络增强问答系统的系统性标准。通过多维人类评估与定量消融实验，表明所提出的WebGLM设计优于现有系统。搭载100亿参数GLM（10B）的WebGLM在人类评估中表现优于同体量WebGPT（13B），甚至与WebGPT（175B）性能相当。代码、演示与数据见\url{https://github.com/THUDM/WebGLM}。