Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment

arXiv:2405.05678v1 Announce Type: cross
Abstract: 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 …

abstract ai systems alignment arxiv beyond challenge communication cs.cl cs.hc emergence generative human interactions llms prompts results significance systems type