paper-with-me

홈 › Papers

Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models

2025-01-13 · Yongyu Mu, Hengyu Li, junxin Wang, Xiaoxuan Zhou, Chenglong Wang, Yingfeng Luo, Qiaozhi He, Tong Xiao, Guocheng Chen, Jingbo Zhu

Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image descriptions to be more detailed and logical. However, as demand for more complex and flexible image descriptions grows, enhancing comprehension of input text within the ICL paradigm remains a critical yet underexplored area. In this work, we extend this line of research by constructing parallel multilingual prompts aimed at harnessing the multilingual capabilities of LMMs. More specifically, we translate the input text into several languages and provide the models with both the original text and the translations. Experiments on two LMMs across 3 benchmarks show that our method, PMT2I, achieves superior performance in general, compositional, and fine-grained assessments, especially in human preference alignment. Additionally, with its advantage of generating more diverse images, PMT2I significantly outperforms baseline prompts when incorporated with reranking methods. Our code and parallel multilingual data can be found at https://github.com/takagi97/PMT2I.

📄 PDF Abstract BibTeX arXiv:2501.07086

Code (1)

takagi97/pmt2i 공식 구현 pytorch

Tasks

Image GenerationIn-Context LearningRerankingText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting

2023-05-31 · Rita Ramos, Bruno Martins, Desmond Elliott

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process. Without requiring any multilingual caption data, we …

DecoderImage CaptioningLanguage ModelingLanguage Modelling+1

Multilingual Prompting for Improving LLM Generation Diversity

2025-05-21 · Qihan Wang, Shidong Pan, Tal Linzen, Emily Black

Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingua…

DiversityHallucination

Instruction Following by Boosting Attention of Large Language Models

2025-06-16 · Vitoria Guardieiro, Adam Stein, Avishree Khare, Eric Wong

Controlling the generation of large language models (LLMs) remains a central challenge to ensure their safe and reliable deployment. While prompt engineering and finetuning are common approaches, recent work has explored…

Instruction FollowingPrompt Engineering

How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting

2025-07-21 · Aman Gupta, Yingying Zhuang, Zhou Yu, Ziji Zhang 외 arxiv

Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retrieval-augmented generation (RAG)-based s…

What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning

2025-11-19 · Jeremias Ferrao, Ezgi Basar, Khondoker Ittehadul Islam, Mahrokh Hassani arxiv

This study investigates the attribution patterns underlying Chain-of-Thought (CoT) reasoning in multilingual LLMs. While prior works demonstrate the role of CoT prompting in improving task performance, there are concerns…