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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Yoonsu, Son, Kihoon, Kim, Seoyoung, Kim, Juho
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913397908439040
author Kim, Yoonsu
Son, Kihoon
Kim, Seoyoung
Kim, Juho
author_facet Kim, Yoonsu
Son, Kihoon
Kim, Seoyoung
Kim, Juho
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment
Kim, Yoonsu
Son, Kihoon
Kim, Seoyoung
Kim, Juho
Human-Computer Interaction
Computation and Language
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.
title Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2405.05678