Conversational Agents.
Mimicking Human Conversation.
A conversational agent is any dialogue system that conducts NLP (Natural Language Processing and responds automatically using human language.
Conversational agents represent the practical implementation of computational linguistics and are usually deployed as chatbots and virtual or AI assistants.
As conversational agents powered by LLMs become more human-like, users are starting to view them as companions rather than mere assistants.
Conversational agents are now blurring the lines between talking to a real person or a bot online.
So how do changes to a user’s mental model of an AI system affect their interaction with the system?
In a research participants interacted with the same conversational AI, but were influenced by different priming statements regarding the AI’s inner motives such as caring, manipulative or no motives.
This showed that those who perceived a caring motive for the AI also perceived it as more trustworthy, empathetic and better performing and that the effects of priming and initial mental models were stronger for a more sophisticated AI model.
