Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition

2025-01-19

AI Summary

In multi-step complex semantic tasks—such as compound fact-checking—humans often struggle to calibrate appropriate trust in AI, particularly when AI generates misleading outputs. Method: We propose a fine-grained “appropriate reliance” evaluation framework integrating LLM-driven task decomposition, controlled experiments (N=233), and behavioral log modeling to systematically investigate the mechanisms through which multi-step transparent decision processes influence human-AI interaction. Contribution: This work is the first to empirically demonstrate that multi-step transparency significantly improves decision accuracy under misleading conditions (+18.7%). It identifies users’ “scrutiny of intermediate steps” as a critical moderating variable. Furthermore, it delineates the boundary conditions and underlying cognitive mechanisms governing transparency’s efficacy—thereby providing both theoretical grounding and empirical evidence for designing trustworthy human-AI collaboration systems.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Security and Privacy: Data transparency and provenance

Abstract

In recent years, the rapid development of AI systems has brought about the benefits of intelligent services but also concerns about security and reliability. By fostering appropriate user reliance on an AI system, both complementary team performance and reduced human workload can be achieved. Previous empirical studies have extensively analyzed the impact of factors ranging from task, system, and human behavior on user trust and appropriate reliance in the context of one-step decision making. However, user reliance on AI systems in tasks with complex semantics that require multi-step workflows remains under-explored. Inspired by recent work on task decomposition with large language models, we propose to investigate the impact of a novel Multi-Step Transparent (MST) decision workflow on user reliance behaviors. We conducted an empirical study (N = 233) of AI-assisted decision making in composite fact-checking tasks (i.e., fact-checking tasks that entail multiple sub-fact verification steps). Our findings demonstrate that human-AI collaboration with an MST decision workflow can outperform one-step collaboration in specific contexts (e.g., when advice from an AI system is misleading). Further analysis of the appropriate reliance at fine-grained levels indicates that an MST decision workflow can be effective when users demonstrate a relatively high consideration of the intermediate steps. Our work highlights that there is no one-size-fits-all decision workflow that can help obtain optimal human-AI collaboration. Our insights help deepen the understanding of the role of decision workflows in facilitating appropriate reliance. We synthesize important implications for designing effective means to facilitate appropriate reliance on AI systems in composite tasks, positioning opportunities for the human-centered AI and broader HCI communities.

Problem

• Human-AI Interaction
• Multi-step Tasks
• Effective Collaboration

Innovation

• Multi-step Transparent Decision-making Process
• Enhanced Human-AI Collaboration
• Task-dependent Decision Flow Adjustment