Bridging UI Design and chatbot Interactions: Applying Form-Based Principles to Conversational Agents
This addresses the issue of ambiguous interactions in chatbots for users in domains like hotel booking and customer management, but it is incremental as it adapts existing GUI principles to conversational agents.
The paper tackled the problem of confusion and incomplete context management in domain-specific chatbots by modeling GUI-inspired metaphors like acknowledgment and context switching as explicit tasks within LLM prompts, resulting in improvements in multi-turn task coherence, user satisfaction, and efficiency.
Domain specific chatbot applications often involve multi step interactions, such as refining search filters, selecting multiple items, or performing comparisons. Traditional graphical user interfaces (GUIs) handle these workflows by providing explicit "Submit" (commit data) and "Reset" (discard data) actions, allowing back-end systems to track user intent unambiguously. In contrast, conversational agents rely on subtle language cues, which can lead to confusion and incomplete context management. This paper proposes modeling these GUI inspired metaphors acknowledgment (submit like) and context switching (reset-like) as explicit tasks within large language model (LLM) prompts. By capturing user acknowledgment, reset actions, and chain of thought (CoT) reasoning as structured session data, we preserve clarity, reduce user confusion, and align domain-specific chatbot interactions with back-end logic. We demonstrate our approach in hotel booking and customer management scenarios, highlighting improvements in multi-turn task coherence, user satisfaction, and efficiency.