Position: Towards Bidirectional Human-AI Alignment

2024/06/13 by Hua Shen, Shen, Hua, Tiffany Knearem +47 · 2 voices · 15 citations
Business, Management and Accounting · Computer Science · Engineering · Social Sciences · #Artificial Intelligence (cs.AI) #Big Data and Business Intelligence #Computation and Language (cs.CL) #Digital Transformation in Industry #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #cs.AI #cs.CL #cs.HC

paper · pdf · doi:10.48550/arxiv.2406.09264

openalex publication_date 2024/06/13 · arxiv published 2024/06/13 · openalex created_date 2024/06/15 · arxiv updated 2025/09/29 · openalex updated_date 2026/07/28

Abstract

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and cross-disciplinary collaboration. In this position paper, we argue that the research community should explicitly define and critically reflect on "alignment" to account for the bidirectional and dynamic relationship between humans and AI. Through a systematic review of over 400 papers spanning HCI, NLP, ML, and more, we examine how alignment is currently defined and operationalized. Building on this analysis, we introduce the Bidirectional Human-AI Alignment framework, which not only incorporates traditional efforts to align AI with human values but also introduces the critical, underexplored dimension of aligning humans with AI -- supporting cognitive, behavioral, and societal adaptation to rapidly advancing AI technologies. Our findings reveal significant gaps in current literature, especially in long-term interaction design, human value modeling, and mutual understanding. We conclude with three central challenges and actionable recommendations to guide future research toward more nuanced, reciprocal, and human-AI alignment approaches.

Cited by

• LVLM-Aided Alignment of Task-Specific Vision Models
• Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores
• When Assisting One Disempowers Another
• Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences
• Instrumental goals in advanced AI systems: Features to be managed and not failures to be eliminated?
• The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem
• RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People
• Autonomy Matters: A Study on Personalization-Privacy Dilemma in LLM Agents
• 'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs
• DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
• The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
• Goal-Directedness is in the Eye of the Beholder
• A Comprehensive Evaluation framework of Alignment Techniques for LLMs
• Towards Integrated Alignment
• Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires

Discussions

• Thrilled to share that our paper “Towards Bidirectional Human-AI Alignment” has been accepted to #NeurIPS2025 (Position Track)! 🎉 - NeurIPS 2025 Position Paper: arxiv.org/pdf/2406.09264 🧡Huge thanks [bsky, 3 points, 0 comments]
• Thank you to Dr @huashen.bsky.social and the organizing committee for a productive session. You can view the research framework for "bidirectional human-AI alignment" here: arxiv.org/pdf/2406.09264 [bsky, 1 points, 0 comments]

Related

• Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures
• Align AI to Dynamic Human-AI Workflows
• Understanding the Process of Human-AI Value Alignment
• Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
• Concept Alignment