arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01343cs.CLcs.AI
收藏

CHOPS:基于大语言模型与客户画像系统的客户服务聊天

CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs

Tsinghua University(清华大学);CPHOS;University of Washington(华盛顿大学);University of Copenhagen(哥本哈根大学)

Jingzhe Shi, Jialuo Li, Qinwei Ma, Zaiwen Yang, Huan Ma, Lei Li

AI总结:

针对LLM客户服务与客户画像集成不足及操作能力欠缺的问题,提出CHOPS代理,结合大小模型高效利用现有系统,提供准确响应并避免有害操作,在CPHOS数据集上验证其性能。

摘要:

企业和软件平台越来越多地转向使用大型语言模型(LLM),如GPT-3.5、GPT-4、GLM-3和LLaMa-2,用于提供文件访问的聊天辅助或作为客户服务的推理代理。然而,当前基于LLM的客户服务模型与客户画像的集成有限,并且缺乏有效服务所必需的操作能力。此外,现有的API集成强调多样性,而忽视了真实客户服务场景中至关重要的精确性和错误避免。为解决这些问题,我们提出了一个名为CHOPS(CHat with custOmer Profile in existing System)的LLM代理,旨在:(1)高效利用现有数据库或系统,按照现有指南访问用户信息或与这些系统交互;(2)提供准确合理的响应或在系统中执行所需操作,同时避免有害操作;(3)结合小型和大型LLM,以合理的推理成本实现满意的性能。我们引入了一个实用数据集CPHOS-dataset,该数据集包含数据库、指导文件和从CPHOS(一个促进高中教师和学生组织模拟物理奥林匹克竞赛的在线平台)收集的问答对。我们使用CPHOS-dataset进行了大量实验,以验证我们提出的CHOPS架构的性能,旨在展示LLM如何增强或替代人工客户服务。我们提出的架构和数据集的代码可在{https://github.com/JingzheShi/CHOPS}找到。

英文摘要:

Businesses and software platforms are increasingly turning to Large Language Models (LLMs) such as GPT-3.5, GPT-4, GLM-3, and LLaMa-2 for chat assistance with file access or as reasoning agents for customer service. However, current LLM-based customer service models have limited integration with customer profiles and lack the operational capabilities necessary for effective service. Moreover, existing API integrations emphasize diversity over the precision and error avoidance essential in real-world customer service scenarios. To address these issues, we propose an LLM agent named CHOPS (CHat with custOmer Profile in existing System), designed to: (1) efficiently utilize existing databases or systems for accessing user information or interacting with these systems following existing guidelines; (2) provide accurate and reasonable responses or carry out required operations in the system while avoiding harmful operations; and (3) leverage a combination of small and large LLMs to achieve satisfying performance at a reasonable inference cost. We introduce a practical dataset, the CPHOS-dataset, which includes a database, guiding files, and QA pairs collected from CPHOS, an online platform that facilitates the organization of simulated Physics Olympiads for high school teachers and students. We have conducted extensive experiments to validate the performance of our proposed CHOPS architecture using the CPHOS-dataset, with the aim of demonstrating how LLMs can enhance or serve as alternatives to human customer service. Code for our proposed architecture and dataset can be found at {https://github.com/JingzheShi/CHOPS}.

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。

↑