Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913874729500672 |
|---|---|
| author | Wang, Xiaonan Shao, Bo Kim, Hansaem |
| author_facet | Wang, Xiaonan Shao, Bo Kim, Hansaem |
| contents | Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. However, current benchmarks remain coarse-grained, linguistically biased, and lack multimodal and privacy-aware evaluations. To address these gaps, we present KoreaGEO Bench, the first fine-grained, multimodal geolocation benchmark for Korean street views. Our dataset comprises 1,080 high-resolution images sampled across four urban clusters and nine place types, enriched with multi-contextual annotations and two styles of Korean captions simulating real-world privacy exposure. We introduce a three-path evaluation protocol to assess ten mainstream VLMs under varying input modalities and analyze their accuracy, spatial bias, and reasoning behavior. Results reveal modality-driven shifts in localization precision and highlight structural prediction biases toward core cities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views Wang, Xiaonan Shao, Bo Kim, Hansaem Computer Vision and Pattern Recognition Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. However, current benchmarks remain coarse-grained, linguistically biased, and lack multimodal and privacy-aware evaluations. To address these gaps, we present KoreaGEO Bench, the first fine-grained, multimodal geolocation benchmark for Korean street views. Our dataset comprises 1,080 high-resolution images sampled across four urban clusters and nine place types, enriched with multi-contextual annotations and two styles of Korean captions simulating real-world privacy exposure. We introduce a three-path evaluation protocol to assess ten mainstream VLMs under varying input modalities and analyze their accuracy, spatial bias, and reasoning behavior. Results reveal modality-driven shifts in localization precision and highlight structural prediction biases toward core cities. |
| title | Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03371 |