Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment
This addresses the critical challenge of ensuring AI produces intended outcomes for users, particularly with generative AI, but is incremental as it applies known human strategies to AI design.
The paper tackles the problem of AI intent alignment by studying human-human communication strategies to improve AI systems' understanding of user intent, aiming to advance human-centered AI design.
AI intent alignment, ensuring that AI produces outcomes as intended by users, is a critical challenge in human-AI interaction. The emergence of generative AI, including LLMs, has intensified the significance of this problem, as interactions increasingly involve users specifying desired results for AI systems. In order to support better AI intent alignment, we aim to explore human strategies for intent specification in human-human communication. By studying and comparing human-human and human-LLM communication, we identify key strategies that can be applied to the design of AI systems that are more effective at understanding and aligning with user intent. This study aims to advance toward a human-centered AI system by bringing together human communication strategies for the design of AI systems.