Information for Conversation Generation: Proposals Utilising Knowledge Graphs
This addresses conversational AI limitations for users seeking more engaging and reliable chatbots, but it appears incremental as it builds on existing knowledge graph techniques.
The paper tackles the problem of low-quality LLM-generated conversations by proposing three knowledge graph-based methods to improve relevance, emotional alignment, and character consistency, though no concrete performance numbers are provided.
LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional capability, and an inability to maintain a consistent character. Knowledge graphs are commonly used forms of external knowledge and may provide solutions to these challenges. This paper introduces three proposals, utilizing knowledge graphs to enhance LLM generation. Firstly, dynamic knowledge graph embeddings and recommendation could allow for the integration of new information and the selection of relevant knowledge for response generation. Secondly, storing entities with emotional values as additional features may provide knowledge that is better emotionally aligned with the user input. Thirdly, integrating character information through narrative bubbles would maintain character consistency, as well as introducing a structure that would readily incorporate new information.