Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Shuai, Chen, Qiaoyi, Wang, Xinru, Zheng, Chengbo, Peng, Zhenhui, Yin, Ming, Ma, Xiaojuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915191974789120
author Ma, Shuai
Chen, Qiaoyi
Wang, Xinru
Zheng, Chengbo
Peng, Zhenhui
Yin, Ming
Ma, Xiaojuan
author_facet Ma, Shuai
Chen, Qiaoyi
Wang, Xinru
Zheng, Chengbo
Peng, Zhenhui
Yin, Ming
Ma, Xiaojuan
contents In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16812
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making
Ma, Shuai
Chen, Qiaoyi
Wang, Xinru
Zheng, Chengbo
Peng, Zhenhui
Yin, Ming
Ma, Xiaojuan
Human-Computer Interaction
Artificial Intelligence
In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.
title Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2403.16812