Situation Graph Prediction: Structured Perspective Inference for User Modeling
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_ | 1866914329079578624 |
|---|---|
| author | Shin, Jisung Platnick, Daniel Alirezaie, Marjan Rahnama, Hossein |
| author_facet | Shin, Jisung Platnick, Daniel Alirezaie, Marjan Rahnama, Hossein |
| contents | Perspective-Aware AI requires modeling evolving internal states--goals, emotions, contexts--not merely preferences. Progress is limited by a data bottleneck: digital footprints are privacy-sensitive and perspective states are rarely labeled. We propose Situation Graph Prediction (SGP), a task that frames perspective modeling as an inverse inference problem: reconstructing structured, ontology-aligned representations of perspective from observable multimodal artifacts. To enable grounding without real labels, we use a structure-first synthetic generation strategy that aligns latent labels and observable traces by design. As a pilot, we construct a dataset and run a diagnostic study using retrieval-augmented in-context learning as a proxy for supervision. In our study with GPT-4o, we observe a gap between surface-level extraction and latent perspective inference--indicating latent-state inference is harder than surface extraction under our controlled setting. Results suggest SGP is non-trivial and provide evidence for the structure-first data synthesis strategy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13319 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Situation Graph Prediction: Structured Perspective Inference for User Modeling Shin, Jisung Platnick, Daniel Alirezaie, Marjan Rahnama, Hossein Artificial Intelligence Human-Computer Interaction Perspective-Aware AI requires modeling evolving internal states--goals, emotions, contexts--not merely preferences. Progress is limited by a data bottleneck: digital footprints are privacy-sensitive and perspective states are rarely labeled. We propose Situation Graph Prediction (SGP), a task that frames perspective modeling as an inverse inference problem: reconstructing structured, ontology-aligned representations of perspective from observable multimodal artifacts. To enable grounding without real labels, we use a structure-first synthetic generation strategy that aligns latent labels and observable traces by design. As a pilot, we construct a dataset and run a diagnostic study using retrieval-augmented in-context learning as a proxy for supervision. In our study with GPT-4o, we observe a gap between surface-level extraction and latent perspective inference--indicating latent-state inference is harder than surface extraction under our controlled setting. Results suggest SGP is non-trivial and provide evidence for the structure-first data synthesis strategy. |
| title | Situation Graph Prediction: Structured Perspective Inference for User Modeling |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.13319 |