Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions

2024-06-13

arXiv.org

AI Summary

Current AI alignment research is hindered by conceptual ambiguity and a unidirectional, static paradigm (AI→human), impeding interdisciplinary collaboration and practical progress. To address this, we conduct a systematic literature review (SLR) of over 400 cross-disciplinary publications from 2019–2024. Our analysis yields the first “bidirectional human-AI alignment” framework: it formalizes not only AI’s adaptation to human goals and values but also humans’ cognitive recalibration to AI capabilities and limitations—emphasizing dynamism, interaction, and long-term co-evolution. As the first human-centered, integrative conceptual model, it bridges theoretical divides across HCI, NLP, and ML; clarifies definitional boundaries of alignment; identifies critical research gaps and core value dimensions; and synthesizes three key future challenges with actionable pathways. This work establishes a unified discourse and a foundational research roadmap for the alignment field.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Recent advancements in general-purpose AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. However, the lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. In particular, ML- and philosophy-oriented alignment research often views AI alignment as a static, unidirectional process (i.e., aiming to ensure that AI systems' objectives match humans) rather than an ongoing, mutual alignment problem. This perspective largely neglects the long-term interaction and dynamic changes of alignment. To understand these gaps, we introduce a systematic review of over 400 papers published between 2019 and January 2024, spanning multiple domains such as Human-Computer Interaction (HCI), Natural Language Processing (NLP), Machine Learning (ML). We characterize, define and scope human-AI alignment. From this, we present a conceptual framework of"Bidirectional Human-AI Alignment"to organize the literature from a human-centered perspective. This framework encompasses both 1) conventional studies of aligning AI to humans that ensures AI produces the intended outcomes determined by humans, and 2) a proposed concept of aligning humans to AI, which aims to help individuals and society adjust to AI advancements both cognitively and behaviorally. Additionally, we articulate the key findings derived from literature analysis, including literature gaps and trends, human values, and interaction techniques. To pave the way for future studies, we envision three key challenges and give recommendations for future research.

Problem

• Defining and clarifying the concept of AI alignment
• Examining bidirectional human-AI relationships and gaps
• Addressing human adaptation to advancing AI technologies

Innovation

• Introduces Bidirectional Human-AI Alignment framework
• Aligns AI with human values and vice versa
• Supports human adaptation to advancing AI technologies