{"id":28355417,"url":"https://github.com/henrypengzou/implicitave","last_synced_at":"2025-10-26T20:39:21.466Z","repository":{"id":221059418,"uuid":"753308500","full_name":"HenryPengZou/ImplicitAVE","owner":"HenryPengZou","description":"[ACL 2024] Dataset and Code of \"ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction\"","archived":false,"fork":false,"pushed_at":"2024-06-10T22:42:20.000Z","size":81812,"stargazers_count":13,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-04T10:05:14.269Z","etag":null,"topics":["attribute-value-extraction","implicit-attribute-value-extraction","multimodal-llm","vision-language-model"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2404.15592","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/HenryPengZou.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-05T21:35:45.000Z","updated_at":"2025-05-03T22:58:46.000Z","dependencies_parsed_at":"2024-06-11T00:55:28.622Z","dependency_job_id":null,"html_url":"https://github.com/HenryPengZou/ImplicitAVE","commit_stats":null,"previous_names":["henrypengzou/implicitave"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/HenryPengZou/ImplicitAVE","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HenryPengZou%2FImplicitAVE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HenryPengZou%2FImplicitAVE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HenryPengZou%2FImplicitAVE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HenryPengZou%2FImplicitAVE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HenryPengZou","download_url":"https://codeload.github.com/HenryPengZou/ImplicitAVE/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HenryPengZou%2FImplicitAVE/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260927142,"owners_count":23083965,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attribute-value-extraction","implicit-attribute-value-extraction","multimodal-llm","vision-language-model"],"created_at":"2025-05-28T04:10:39.030Z","updated_at":"2025-10-26T20:39:21.461Z","avatar_url":"https://github.com/HenryPengZou.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction\n\n![Task](pipeline.jpg)\n\nThis repository contains the dataset and code of the paper:\n\u003e **ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction** \n\u003e [[Paper]](https://arxiv.org/pdf/2404.15592) [[arXiv]](https://arxiv.org/abs/2404.15592) [[ACL Anthology]]() [[OpenReview]](https://openreview.net/forum?id=HSZjfit7sS)  \u003cbr\u003e\n\u003e Accepted by ACL 2024 Findings \u003cbr\u003e\n\u003e ACL ARR Feb Scores: Soundness - 4/4/4, Overall Assessment - 4/3.5/3.5, Meta - 4 \u003cbr\u003e\n\u003e Henry Peng Zou, Vinay Samuel, Yue Zhou, Weizhi Zhang, Liancheng Fang, Zihe Song, Philip S. Yu, Cornelia Caragea \u003cbr\u003e\n\n\n## Datasets\nOur evaluation and training data are released in the [data](https://github.com/HenryPengZou/ImplicitAVE/tree/main/data) folder. For product images, please download them from the provided links in the corresponding folder and unzip them into the same folder.\n\n\n## Code\nThe inference code we used for [GPT-4V](https://platform.openai.com/docs/models), [BLIP-2](https://github.com/salesforce/LAVIS/tree/main/projects/blip2), [InstructBLIP](https://github.com/salesforce/LAVIS/tree/main/projects/instructblip), [LLaVA](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file), [Qwen-VL](https://github.com/QwenLM/Qwen-VL), and [Qwen-VL-Chat](https://github.com/QwenLM/Qwen-VL) are provided. When running the inference code for each MLLM, please refer to the instruction in the corresponding projects for environment setup and package installation. \n\nHere we provide an example for setting up the environment, running the inference and evaluation code for [Qwen](https://github.com/HenryPengZou/ImplicitAVE/tree/main/code/Qwen_VL):\n\n## Setup\n```bash\n# Environment setup\nconda create -n Qwen python=3.9 -y\nconda activate Qwen\n\n# install pytorch\nconda install pytorch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2 pytorch-cuda=11.8 -c pytorch -c nvidia\n\n# install dependency\n# cd code/Qwen-VL\npip install -r requirements.txt\n```\n\n## Evaluation\n\nTo start the inference and evaluation, simply run `Qwen_VL_7B.ipynb` and `Qwen_VL_Chat.ipynb` notebooks.\n\n\nYou might need to change the paths to your own data paths and replace the model names with other variants you would like to use.\n\n\n## Bugs or Questions\n\nIf you have any questions related to the dataset or the paper, feel free to email Henry Peng Zou (pzou3@uic.edu) and Vinay Samuel(vsamuel@andrew.cmu.edu). If you encounter any problems when using the code, or want to report a bug, you can open an issue. Please try to specify the problem with details so we can help you better and quicker!\n\n\n## Citation\nIf you find this repository helpful, please consider citing our paper 💕: \n```bibtex\n@article{zou2024implicitave,\n    title={ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction},\n    author={Henry Peng Zou and Vinay Samuel and Yue Zhou and Weizhi Zhang and Liancheng Fang and Zihe Song and Philip S. Yu and Cornelia Caragea},\n    journal={arXiv preprint arXiv:2404.15592},\n    year={2024}\n}\n```\n\n## Acknowledgement\nThis repo borrows some data and codes from [MAVE](https://github.com/google-research-datasets/MAVE), [LaVIN](https://github.com/luogen1996/LaVIN/tree/main) and [Llama](https://github.com/meta-llama/llama), [GPT-4V](https://platform.openai.com/docs/models), [BLIP-2](https://github.com/salesforce/LAVIS/tree/main/projects/blip2), [InstructBLIP](https://github.com/salesforce/LAVIS/tree/main/projects/instructblip), [LLaVA](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file), [Qwen-VL](https://github.com/QwenLM/Qwen-VL), and [Qwen-VL-Chat](https://github.com/QwenLM/Qwen-VL). We appreciate their great works! \u003cbr\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhenrypengzou%2Fimplicitave","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhenrypengzou%2Fimplicitave","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhenrypengzou%2Fimplicitave/lists"}