Control in Hybrid Chatbots
This addresses the challenge for businesses seeking to combine structured data with AI capabilities while ensuring reliability, though it appears incremental as it builds on existing integration approaches.
The paper tackles the problem of integrating rule-based knowledge bases with neural chatbots to maintain control and prevent model hallucination, presenting a case study on a commercial rule engine integration and discussing alternative methods.
Customer data typically is held in database systems, which can be seen as rule-based knowledge base, whereas businesses increasingly want to benefit from the capabilities of large, pre-trained language models. In this technical report, we describe a case study of how a commercial rule engine and an integrated neural chatbot may be integrated, and what level of control that particular integration mode leads to. We also discuss alternative ways (including past ways realized in other systems) how researchers strive to maintain control and avoid what has recently been called model "hallucination".