Applications
Multi-turn Dialogue
Multi-turn dialogue requires the AI to track conversation history, resolve coreferences ("What did you mean by that?"), maintain consistency, and update its understanding as new information is introduced. This is distinct from single-turn QA where each question is independent.
Context window size limits multi-turn conversations: older exchanges may be truncated. Techniques like conversation summarization, selective context retention, and external memory stores extend effective multi-turn conversation length.
Authority Links
Related Terms
Applications
Dialogue System
AI system designed to carry on natural, coherent conversations with human users.
Model Components
Context Window
The maximum number of tokens a language model can process in a single inference pass — everything the model "sees" at once, including system prompt, conversation history, retrieved documents, and the response being generated.
Techniques & Methods
Coreference Resolution
Determining which words or phrases in text refer to the same real-world entity.
Applications
Chatbot
Software application that simulates human conversation via text or voice interfaces.