Position: Towards Bidirectional Human-AI Alignment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914062999224320 |
|---|---|
| author | Shen, Hua Knearem, Tiffany Ghosh, Reshmi Alkiek, Kenan Krishna, Kundan Liu, Yachuan Ma, Ziqiao Petridis, Savvas Peng, Yi-Hao Qiwei, Li Rakshit, Sushrita Si, Chenglei Xie, Yutong Bigham, Jeffrey P. Bentley, Frank Chai, Joyce Lipton, Zachary Mei, Qiaozhu Mihalcea, Rada Terry, Michael Yang, Diyi Morris, Meredith Ringel Resnick, Paul Jurgens, David |
| author_facet | Shen, Hua Knearem, Tiffany Ghosh, Reshmi Alkiek, Kenan Krishna, Kundan Liu, Yachuan Ma, Ziqiao Petridis, Savvas Peng, Yi-Hao Qiwei, Li Rakshit, Sushrita Si, Chenglei Xie, Yutong Bigham, Jeffrey P. Bentley, Frank Chai, Joyce Lipton, Zachary Mei, Qiaozhu Mihalcea, Rada Terry, Michael Yang, Diyi Morris, Meredith Ringel Resnick, Paul Jurgens, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09264 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Position: Towards Bidirectional Human-AI Alignment Shen, Hua Knearem, Tiffany Ghosh, Reshmi Alkiek, Kenan Krishna, Kundan Liu, Yachuan Ma, Ziqiao Petridis, Savvas Peng, Yi-Hao Qiwei, Li Rakshit, Sushrita Si, Chenglei Xie, Yutong Bigham, Jeffrey P. Bentley, Frank Chai, Joyce Lipton, Zachary Mei, Qiaozhu Mihalcea, Rada Terry, Michael Yang, Diyi Morris, Meredith Ringel Resnick, Paul Jurgens, David Human-Computer Interaction Artificial Intelligence Computation and Language 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. |
| title | Position: Towards Bidirectional Human-AI Alignment |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2406.09264 |