{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:45:49Z","timestamp":1781279149621,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,9]]},"DOI":"10.1109\/ipas63548.2025.10924504","type":"proceedings-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:29:13Z","timestamp":1742603353000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["How Culturally Aware Are Vision-Language Models?"],"prefix":"10.1109","author":[{"given":"Olena","family":"Burda-Lassen","sequence":"first","affiliation":[{"name":"Independent Research Scientist,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aman","family":"Chadha","sequence":"additional","affiliation":[{"name":"Stanford University\/Amazon Inc.,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shashank","family":"Goswami","sequence":"additional","affiliation":[{"name":"Independent Research Scientist,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinija","family":"Jain","sequence":"additional","affiliation":[{"name":"Stanford University,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Flamingo: a Visual Language Model for Few-Shot Learning","author":"Alayrac","year":"2022"},{"key":"ref3","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref4","article-title":"OpenFlamingo: an Open-Source framework for training large autoregressive Vision-Language models","author":"Awadalla","year":"2023"},{"key":"ref5","article-title":"TouchStone: Evaluating Vision-Language Models by Language Models","author":"Bai","year":"2023"},{"key":"ref6","article-title":"Machine Translation of Folktales: small-datadriven and LLM-based approaches","volume-title":"ACL Anthology","author":"Burda-Lassen","year":"2023"},{"key":"ref7","article-title":"Ukrainian-To-English Folktale Corpus: Parallel Corpus Creation and augmentation for Machine Translation in Low-Resource Languages","volume-title":"ACL Anthology","author":"Burda-Lassen","year":"2022"},{"key":"ref8","article-title":"Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing","author":"Cao","year":"2024"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-68796-0_36","article-title":"Iconographic image captioning for artworks","author":"Cetinic","year":"2021"},{"key":"ref10","article-title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","author":"Dai","year":"2023"},{"key":"ref11","article-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language models","author":"Fu","year":"2023"},{"key":"ref12","article-title":"Language Is Not All You Need: Aligning Perception with Language Models","author":"Huang","year":"2023"},{"key":"ref13","article-title":"How well do LLMs represent values across cultures? Empirical analysis of LLM responses based on Hofstede Cultural dimensions","author":"Kharchenko","year":"2024"},{"key":"ref14","article-title":"IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images","author":"Krishna","year":"2023"},{"key":"ref15","article-title":"Multimodal foundation models: from specialists to General-Purpose Assistants","author":"Li","year":"2023"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.emnlp-main.20","article-title":"Evaluating object hallucination in large Vision-Language models","author":"Li","year":"2023"},{"key":"ref17","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref18","article-title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","author":"McKinzie","year":"2024"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-main.329","article-title":"Benchmarking Vision language models for cultural understanding","author":"Nayak","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_1"},{"key":"ref21","article-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024"},{"key":"ref22","article-title":"GIT: a generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref23","article-title":"Woodpecker: Hallucination Correction for Multimodal large Language models","author":"Yin","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01178-8"}],"event":{"name":"2025 IEEE 6th International Conference on Image Processing, Applications and Systems (IPAS)","location":"Lyon, France","start":{"date-parts":[[2025,1,9]]},"end":{"date-parts":[[2025,1,11]]}},"container-title":["2025 IEEE 6th International Conference on Image Processing, Applications and Systems (IPAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10924471\/10924472\/10924504.pdf?arnumber=10924504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T17:52:42Z","timestamp":1742838762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ipas63548.2025.10924504","relation":{},"subject":[],"published":{"date-parts":[[2025,1,9]]}}}