Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models
- URL: http://arxiv.org/abs/2409.01584v1
- Date: Tue, 3 Sep 2024 03:42:56 GMT
- Title: Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models
- Authors: Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe,
- Abstract summary: This study created an extended dataset in multiple languages without relying on machine translation.
It examined whether Instruction-Tuning in resource-rich English improves performance in other languages.
- Score: 28.716852515539497
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow. However, pre-training of Vision Encoder and the integrated training of LLMs with Vision Encoder are mainly conducted using English training data, leaving it uncertain whether LVLMs can completely handle their potential when generating explanations in languages other than English. In addition, multilingual QA benchmarks that create datasets using machine translation have cultural differences and biases, remaining issues for use as evaluation tasks. To address these challenges, this study created an extended dataset in multiple languages without relying on machine translation. This dataset that takes into account nuances and country-specific phrases was then used to evaluate the generation explanation abilities of LVLMs. Furthermore, this study examined whether Instruction-Tuning in resource-rich English improves performance in other languages. Our findings indicate that LVLMs perform worse in languages other than English compared to English. In addition, it was observed that LVLMs struggle to effectively manage the knowledge learned from English data.
Related papers
- Pruning Multilingual Large Language Models for Multilingual Inference [28.36717615166238]
This study explores how to enhance the zero-shot performance of MLLMs in non-English languages.
We first analyze the behavior of MLLMs when performing translation and reveal that there are large magnitude features that play a critical role in the translation process.
arXiv Detail & Related papers (2024-09-25T13:15:50Z) - Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters [3.7273829129985305]
This paper explores integration of graph knowledge from linguistic into multilingual Large Models (LLMs)
We employ language-specific adapters to improve performance for low-resource languages (LRLs) in sentiment analysis (SA) and named entity recognition (NER)
We assess how structured graph knowledge affects the performance of multilingual LLMs for LRLs in SA and NER.
arXiv Detail & Related papers (2024-07-01T15:56:24Z) - MindMerger: Efficient Boosting LLM Reasoning in non-English Languages [26.334092384176518]
Reasoning capabilities are crucial for Large Language Models (LLMs)
We propose MindMerger, which merges LLMs with the external language understanding capabilities from multilingual models.
MindMerger consistently outperforms all baselines, especially in low-resource languages.
arXiv Detail & Related papers (2024-05-27T17:41:54Z) - Enhancing Multilingual Capabilities of Large Language Models through
Self-Distillation from Resource-Rich Languages [60.162717568496355]
Large language models (LLMs) have been pre-trained on multilingual corpora.
Their performance still lags behind in most languages compared to a few resource-rich languages.
arXiv Detail & Related papers (2024-02-19T15:07:32Z) - UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised
Fine-tuning Dataset [69.33424532827608]
Open-source large language models (LLMs) have gained significant strength across diverse fields.
In this work, we construct an open-source multilingual supervised fine-tuning dataset.
The resulting UltraLink dataset comprises approximately 1 million samples across five languages.
arXiv Detail & Related papers (2024-02-07T05:05:53Z) - Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation [64.5862977630713]
This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task.
We find that reference information significantly enhances the evaluation accuracy, while surprisingly, source information sometimes is counterproductive.
arXiv Detail & Related papers (2024-01-12T13:23:21Z) - Zero-Shot Cross-Lingual Reranking with Large Language Models for
Low-Resource Languages [51.301942056881146]
We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages.
Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba)
We examine cross-lingual reranking with queries in English and passages in the African languages.
arXiv Detail & Related papers (2023-12-26T18:38:54Z) - CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large
Language Models in 167 Languages [86.90220551111096]
Training datasets for large language models (LLMs) are often not fully disclosed.
We present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages.
arXiv Detail & Related papers (2023-09-17T23:49:10Z) - Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars.
We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English.
Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
arXiv Detail & Related papers (2023-06-20T08:27:47Z) - El Departamento de Nosotros: How Machine Translated Corpora Affects
Language Models in MRC Tasks [0.12183405753834563]
Pre-training large-scale language models (LMs) requires huge amounts of text corpora.
We study the caveats of applying directly translated corpora for fine-tuning LMs for downstream natural language processing tasks.
We show that careful curation along with post-processing lead to improved performance and overall LMs robustness.
arXiv Detail & Related papers (2020-07-03T22:22:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.