Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918528790036480 |
|---|---|
| author | da Silva, Neemias Delgado, Myriam Minetto, Rodrigo Silver, Daniel Silva, Thiago H |
| author_facet | da Silva, Neemias Delgado, Myriam Minetto, Rodrigo Silver, Daniel Silva, Thiago H |
| contents | We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations from 1,200 persona-conditioned agents and two no-persona settings, we analyze captions, justifications, and perception tags across personas. Results indicate strong convergence in captions for different personas, whereas justifications display systematic variation associated with socioeconomic and political attributes, while perception tags show no statistically significant persona-related differences, though effect trends are observed. Topic analysis further reveals that personas emphasize different evaluative themes when interpreting the same scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29064 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception da Silva, Neemias Delgado, Myriam Minetto, Rodrigo Silver, Daniel Silva, Thiago H Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction Multiagent Systems We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations from 1,200 persona-conditioned agents and two no-persona settings, we analyze captions, justifications, and perception tags across personas. Results indicate strong convergence in captions for different personas, whereas justifications display systematic variation associated with socioeconomic and political attributes, while perception tags show no statistically significant persona-related differences, though effect trends are observed. Topic analysis further reveals that personas emphasize different evaluative themes when interpreting the same scenes. |
| title | Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception |
| topic | Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction Multiagent Systems |
| url | https://arxiv.org/abs/2605.29064 |