Rationalize: Shared Semantic Reasoning for Human-AI Alignment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910271484723200 |
|---|---|
| author | Dasgupta, Aritra Battula, Naga Datha Saikiran Nakarmi, Avina Sen, Sohom Ghosh, Subhodeep Song, Xun |
| author_facet | Dasgupta, Aritra Battula, Naga Datha Saikiran Nakarmi, Avina Sen, Sohom Ghosh, Subhodeep Song, Xun |
| contents | We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30632 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rationalize: Shared Semantic Reasoning for Human-AI Alignment Dasgupta, Aritra Battula, Naga Datha Saikiran Nakarmi, Avina Sen, Sohom Ghosh, Subhodeep Song, Xun Human-Computer Interaction Artificial Intelligence Machine Learning We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches. |
| title | Rationalize: Shared Semantic Reasoning for Human-AI Alignment |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.30632 |