用ASP增强LLM对话可靠性，让机器人真正理解语言
Reliable Conversational Agents under ASP Control that Understand Natural Language
- 用ASP替代LLM做推理，实现可信赖对话
- 框架已成功构建任务型与社交型聊天机器人
- 适合需要高可靠性的对话系统开发者
过去几十年，人们一直在努力让机器像人类一样对话。尽管大语言模型（LLMs）使机器具备类人对话能力，但其缺乏理解力和可靠性的问题广为人知。我们认为，最佳解决方案是仅将LLM作为文本与知识之间的转换器，而对话推理则通过答案集编程（ASP）完成。本文提出一种基于LLM与ASP的框架，用于构建真正理解人类对话的可靠聊天机器人。该框架已应用于开发特定任务聊天机器人及社交机器人。未来研究将聚焦于提升系统的可扩展性与可训练性。
原文摘要 · Abstract (English)
Efforts have been made to make machines converse like humans in the past few decades. The recent techniques of Large Language Models (LLMs) make it possible to have human-like conversations with machines, but LLM's flaws of lacking understanding and reliability are well documented. We believe that the best way to eliminate this problem is to use LLMs only as parsers to translate text to knowledge and vice versa and carry out the conversation by reasoning over this knowledge using the answer set programming. I have been developing a framework based on LLMs and ASP to realize reliable chatbots that "understand" human conversation. This framework has been used to develop task-specific chatbots as well as socialbots. My future research is focused on making these chatbots scalable and trainable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。