Parrot: Multilingual Visual Instruction Tuning

• URL: http://arxiv.org/abs/2406.02539v2
• Date: Sun, 11 Aug 2024 05:15:46 GMT
• Title: Parrot: Multilingual Visual Instruction Tuning
• Authors: Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye,
• Abstract summary: Existing methods mainly focus on aligning vision encoders with Multimodal Large Language Models (MLLMs) We introduce Parrot, a novel method that utilizes textual guidance to drive visual token alignment at the language level. Our method not only demonstrates state-of-the-art performance on multilingual MMBench and MMMB, but also excels across a broad range of multimodal tasks.
• Score: 66.65963606552839
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid development of Multimodal Large Language Models (MLLMs) like GPT-4V has marked a significant step towards artificial general intelligence. Existing methods mainly focus on aligning vision encoders with LLMs through supervised fine-tuning (SFT) to endow LLMs with multimodal abilities, making MLLMs' inherent ability to react to multiple languages progressively deteriorate as the training process evolves. We empirically find that the imbalanced SFT datasets, primarily composed of English-centric image-text pairs, lead to significantly reduced performance in non-English languages. This is due to the failure of aligning the vision encoder and LLM with multilingual tokens during the SFT process. In this paper, we introduce Parrot, a novel method that utilizes textual guidance to drive visual token alignment at the language level. Parrot makes the visual tokens condition on diverse language inputs and uses Mixture-of-Experts (MoE) to promote the alignment of multilingual tokens. Specifically, to enhance non-English visual tokens alignment, we compute the cross-attention using the initial visual features and textual embeddings, the result of which is then fed into the MoE router to select the most relevant experts. The selected experts subsequently convert the initial visual tokens into language-specific visual tokens. Moreover, considering the current lack of benchmarks for evaluating multilingual capabilities within the field, we collect and make available a Massive Multilingual Multimodal Benchmark which includes 6 languages, 15 categories, and 12,000 questions, named as MMMB. Our method not only demonstrates state-of-the-art performance on multilingual MMBench and MMMB, but also excels across a broad range of multimodal tasks. Both the source code and the training dataset of Parrot will be made publicly available. Code is available at: https://github.com/AIDC-AI/Parrot.

Related papers

• Multilingual Large Language Models and Curse of Multilinguality [4.096453902709292]
  Large Language Models (LLMs) have gained large popularity among Natural Language Processing (NLP) researchers and practitioners. This paper navigates the landscape of multilingual LLMs, providing an introductory overview of their technical aspects. It explains underlying architectures, objective functions, pre-training data sources, and tokenization methods.
  arXiv  Detail & Related papers  (2024-06-15T11:31:39Z)
• Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages [3.3227703089509304]
  We propose a simple yet efficient approach to adapt Vision-Language Pre-training to unseen languages using MPLM. Our approach does not require image input and primarily uses machine translation, eliminating the need for target language data.
  arXiv  Detail & Related papers  (2023-06-29T08:20:57Z)
• LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation [94.33019040320507]
  Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features. Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases. We propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.
  arXiv  Detail & Related papers  (2022-10-19T12:21:39Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision [110.66085917826648]
  We develop a technique that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images. "vokenization" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora. Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks.
  arXiv  Detail & Related papers  (2020-10-14T02:11:51Z)
• X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models [103.75890012041366]
  Language models (LMs) have proven surprisingly successful at capturing factual knowledge. However, studies on LMs' factual representation ability have almost invariably been performed on English. We create a benchmark of cloze-style probes for 23 typologically diverse languages.
  arXiv  Detail & Related papers  (2020-10-13T05:29:56Z)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)

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.