ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912889748586496 |
|---|---|
| author | Hegemann, Lena Wen, Xinyi Hedderich, Michael A. Nurmi, Tarmo Subramonyam, Hariharan |
| author_facet | Hegemann, Lena Wen, Xinyi Hedderich, Michael A. Nurmi, Tarmo Subramonyam, Hariharan |
| contents | Generative AI often produces results misaligned with user intentions, for example, resolving ambiguous prompts in unexpected ways. Despite existing approaches to clarify intent, a major challenge remains: understanding and influencing AI's interpretation of user intent through simple, direct inputs requiring no expertise or rigid procedures. We present ToMigo, representing intent as design concept graphs: nodes represent choices of purpose, content, or style, while edges link them with interpretable explanations. Applied to graphic design, ToMigo infers intent from reference images and text. We derived a schema of node types and edges from pre-study data, informing a multimodal large language model to generate graphs aligning nodes externally with user intent and internally toward a unified design goal. This structure enables users to explore AI reasoning and directly manipulate the design concept. In our user studies, ToMigo received high alignment ratings and captured most user intentions well. Users reported greater control and found interactive features-editable graphs, reflective chats, concept-design realignment-useful for evolving and realizing their design ideas. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05825 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent Hegemann, Lena Wen, Xinyi Hedderich, Michael A. Nurmi, Tarmo Subramonyam, Hariharan Human-Computer Interaction Generative AI often produces results misaligned with user intentions, for example, resolving ambiguous prompts in unexpected ways. Despite existing approaches to clarify intent, a major challenge remains: understanding and influencing AI's interpretation of user intent through simple, direct inputs requiring no expertise or rigid procedures. We present ToMigo, representing intent as design concept graphs: nodes represent choices of purpose, content, or style, while edges link them with interpretable explanations. Applied to graphic design, ToMigo infers intent from reference images and text. We derived a schema of node types and edges from pre-study data, informing a multimodal large language model to generate graphs aligning nodes externally with user intent and internally toward a unified design goal. This structure enables users to explore AI reasoning and directly manipulate the design concept. In our user studies, ToMigo received high alignment ratings and captured most user intentions well. Users reported greater control and found interactive features-editable graphs, reflective chats, concept-design realignment-useful for evolving and realizing their design ideas. |
| title | ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.05825 |