Democratizing Chatbot Debugging: A Computational Framework for Evaluating and Explaining Inappropriate Chatbot Responses

Abstract

Evaluating and understanding the inappropriateness of chatbot behaviors can be challenging, particularly for chatbot designers without technical backgrounds. To democratize the debugging process of chatbot misbehaviors for non-technical designers, we propose a framework that leverages dialogue act (DA) modeling to automate the evaluation and explanation of chatbot response inappropriateness. The framework first produces characterizations of context-aware DAs based on discourse analysis theory and real-world human-chatbot transcripts. It then automatically extracts features to identify the appropriateness level of a response and can explain the causes of the inappropriate response by examining the DA mismatch between the response and its conversational context. Using interview chatbots as a testbed, our framework achieves comparable classification accuracy with higher explainability and fewer computational resources than the deep learning baseline, making it the first step in utilizing DAs for chatbot response appropriateness evaluation and explanation.

arXiv comment7 pages, 4 figures, accepted to CUI 2023 poster track

References in corpus (8)

• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Tell Me About Yourself: Using an AI-Powered Chatbot to Conduct Conversational Surveys with Open-ended Questions
• If I Hear You Correctly: Building and Evaluating Interview Chatbots with Active Listening Skills
• Designing Effective Interview Chatbots: Automatic Chatbot Profiling and Design Suggestion Generation for Chatbot Debugging
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• Evaluating Voice Skills by Design Guidelines Using an Automatic Voice Crawler
• Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues