{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-images-to-textual-prompts-zero-shot-vqa","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","arxiv_id":"2212.10846","date":"2022-12-21","proceeding":null,"authors":["Jiaxian Guo","Junnan Li","Dongxu Li","Anthony Meng Huat Tiong","Boyang Li","DaCheng Tao","Steven C. H. Hoi"],"abstract":"Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. However, effective utilization of LLMs for zero-shot visual question-answering (VQA) remains challenging, primarily due to the modality disconnection and task disconnection between LLM and VQA task. End-to-end training on vision and language data may bridge the disconnections, but is inflexible and computationally expensive. To address this issue, we propose \\emph{Img2Prompt}, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training. In order to provide such prompts, we further employ LLM-agnostic models to provide prompts that can describe image content and self-constructed question-answer pairs, which can effectively guide LLM to perform zero-shot VQA tasks. Img2Prompt offers the following benefits: 1) It can flexibly work with various LLMs to perform VQA. 2)~Without the needing of end-to-end training, it significantly reduces the cost of deploying LLM for zero-shot VQA tasks. 3) It achieves comparable or better performance than methods relying on end-to-end training. For example, we outperform Flamingo \\cite{Deepmind:Flamingo2022} by 5.6\\% on VQAv2. On the challenging A-OKVQA dataset, our method even outperforms few-shot methods by as much as 20\\%.","url_abs":"https://arxiv.org/abs/2212.10846v3","url_pdf":"https://arxiv.org/pdf/2212.10846v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"from-images-to-textual-prompts-zero-shot-vqa","repo_url":"https://github.com/salesforce/lavis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"from-images-to-textual-prompts-zero-shot-vqa","repo_url":"https://github.com/abril4416/kgen_vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"from-images-to-textual-prompts-zero-shot-vqa","repo_url":"https://github.com/lastmile-ai/aiconfig","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2212.10846","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}