Reliable Conversational Agents under ASP Control that Understand Natural Language
This addresses the issue of unreliable chatbots for users needing trustworthy interactions, though it appears incremental as it combines existing LLM and ASP methods.
The paper tackles the problem of unreliable and non-understanding conversational agents by proposing a framework that uses Large Language Models (LLMs) only as parsers to translate text to knowledge and vice versa, and carries out conversations via reasoning with answer set programming (ASP), resulting in the development of reliable chatbots for tasks and social interactions.
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.