使用大型语言模型增强基于流水线的对话智能体
Enhancing Pipeline-Based Conversational Agents with Large Language Models
AI总结：
本文研究在设计和运营阶段利用LLM增强基于流水线的对话智能体，提出混合方法以兼顾LLM能力与现有系统隐私及集成保障。
摘要：
人工智能和深度学习的最新进展推动了基于大型语言模型（LLM）的智能体（如GPT-4）的突破。然而，许多商业对话智能体开发工具是基于流水线的，在维持类人对话方面存在局限性。本文研究了LLM在两个阶段增强基于流水线的对话智能体的能力：1）设计和开发阶段；2）运营阶段。在阶段1）中，LLM可以辅助生成训练数据、提取实体和同义词、本地化以及角色设计。在阶段2）中，LLM可以协助进行上下文化、意图分类以防止对话崩溃并处理超出范围的问题、自动纠正话语、重述响应、制定消歧问题、摘要生成以及启用封闭式问答功能。我们在私人银行领域使用GPT-4进行了非正式实验，通过实际示例展示了上述场景。由于隐私担忧和在其现有生态系统中深度集成的需求，公司可能对完全用LLM替换其基于流水线的智能体持谨慎态度。一种将LLM集成到基于流水线的智能体中的混合方法，使公司能够利用LLM的能力节省构建和运行智能体的时间与成本，同时保留其现有系统的集成和隐私保障。
英文摘要：
The latest advancements in AI and deep learning have led to a breakthrough in large language model (LLM)-based agents such as GPT-4. However, many commercial conversational agent development tools are pipeline-based and have limitations in holding a human-like conversation. This paper investigates the capabilities of LLMs to enhance pipeline-based conversational agents during two phases: 1) in the design and development phase and 2) during operations. In 1) LLMs can aid in generating training data, extracting entities and synonyms, localization, and persona design. In 2) LLMs can assist in contextualization, intent classification to prevent conversational breakdown and handle out-of-scope questions, auto-correcting utterances, rephrasing responses, formulating disambiguation questions, summarization, and enabling closed question-answering capabilities. We conducted informal experiments with GPT-4 in the private banking domain to demonstrate the scenarios above with a practical example. Companies may be hesitant to replace their pipeline-based agents with LLMs entirely due to privacy concerns and the need for deep integration within their existing ecosystems. A hybrid approach in which LLMs' are integrated into the pipeline-based agents allows them to save time and costs of building and running agents by capitalizing on the capabilities of LLMs while retaining the integration and privacy safeguards of their existing systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
