Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929548902268928 |
|---|---|
| author | Mukherjee, Anjishnu Zhu, Ziwei Anastasopoulos, Antonios |
| author_facet | Mukherjee, Anjishnu Zhu, Ziwei Anastasopoulos, Antonios |
| contents | We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9,935 images of 67 countries and 10 concept classes; (2) the underlying implicit and potentially stereotypical cultural associations with a cultural artifact extraction task; and (3) an approach to adapt cultural representation in an image based on extracted associations using a modular pipeline, CultureAdapt. We find disparities in cultural understanding at geographic sub-region levels with both open-source (LLaVA) and closed-source (GPT-4V) models on DalleStreet and other existing benchmarks, which we try to understand using over 18,000 artifacts that we identify in association to different countries. Our findings reveal a nuanced picture of the cultural competence of LMMs, highlighting the need to develop culture-aware systems. Dataset and code are available at https://github.com/iamshnoo/crossroads |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02067 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models Mukherjee, Anjishnu Zhu, Ziwei Anastasopoulos, Antonios Computation and Language We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9,935 images of 67 countries and 10 concept classes; (2) the underlying implicit and potentially stereotypical cultural associations with a cultural artifact extraction task; and (3) an approach to adapt cultural representation in an image based on extracted associations using a modular pipeline, CultureAdapt. We find disparities in cultural understanding at geographic sub-region levels with both open-source (LLaVA) and closed-source (GPT-4V) models on DalleStreet and other existing benchmarks, which we try to understand using over 18,000 artifacts that we identify in association to different countries. Our findings reveal a nuanced picture of the cultural competence of LMMs, highlighting the need to develop culture-aware systems. Dataset and code are available at https://github.com/iamshnoo/crossroads |
| title | Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.02067 |