lynx   »   [go: up one dir, main page]

https://trustgen.github.io/
Toolkit: https://github.com/TrustGen/TrustEval-toolkit
Docs of Toolkit: https://trusteval-docs.readthedocs.io/

\n","updatedAt":"2025-02-21T02:25:09.745Z","author":{"_id":"639d94ab7145123e0d44e48a","avatarUrl":"/avatars/5bb6a65b306d1383c4a8bcd9334b470a.svg","fullname":"Yue Huang","name":"HowieHwong","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6227173209190369},"editors":["HowieHwong"],"editorAvatarUrls":["/avatars/5bb6a65b306d1383c4a8bcd9334b470a.svg"],"reactions":[],"isReport":false}},{"id":"67b92aaa30412d4f33d3155d","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264},"createdAt":"2025-02-22T01:38:50.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance](https://huggingface.co/papers/2502.04695) (2025)\n* [Generative AI and LLMs in Industry: A text-mining Analysis and Critical Evaluation of Guidelines and Policy Statements Across Fourteen Industrial Sectors](https://huggingface.co/papers/2501.00957) (2025)\n* [Value Compass Leaderboard: A Platform for Fundamental and Validated Evaluation of LLMs Values](https://huggingface.co/papers/2501.07071) (2025)\n* [SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sector](https://huggingface.co/papers/2501.08814) (2025)\n* [Ethical Concerns of Generative AI and Mitigation Strategies: A Systematic Mapping Study](https://huggingface.co/papers/2502.00015) (2025)\n* [Who is Responsible? The Data, Models, Users or Regulations? Responsible Generative AI for a Sustainable Future](https://huggingface.co/papers/2502.08650) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n\n

Please give a thumbs up to this comment if you found it helpful!

\n

If you want recommendations for any Paper on Hugging Face checkout this Space

\n

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-02-22T01:38:50.596Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7786422371864319},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2502.14296","authors":[{"_id":"67b7e371f17ca6989faa9884","user":{"_id":"639d94ab7145123e0d44e48a","avatarUrl":"/avatars/5bb6a65b306d1383c4a8bcd9334b470a.svg","isPro":false,"fullname":"Yue Huang","user":"HowieHwong","type":"user"},"name":"Yue Huang","status":"extracted_pending","statusLastChangedAt":"2025-02-21T02:22:45.907Z","hidden":false},{"_id":"67b7e371f17ca6989faa9885","user":{"_id":"65a13cb1c5770b27aef2a2bc","avatarUrl":"/avatars/88ec5b988f10ad9fd4d469ae2fa34680.svg","isPro":false,"fullname":"Chujie Gao","user":"Flossie","type":"user"},"name":"Chujie Gao","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:51.964Z","hidden":false},{"_id":"67b7e371f17ca6989faa9886","name":"Siyuan Wu","hidden":false},{"_id":"67b7e371f17ca6989faa9887","user":{"_id":"64b82c659ebb69a79f0073f6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b82c659ebb69a79f0073f6/INEHG7kijEHOhFZMjdBIM.png","isPro":false,"fullname":"Haoran Wang","user":"wang2226","type":"user"},"name":"Haoran Wang","status":"claimed_verified","statusLastChangedAt":"2025-02-24T09:23:23.186Z","hidden":false},{"_id":"67b7e371f17ca6989faa9888","user":{"_id":"66e4aa8d4926518abbf5cae2","avatarUrl":"/avatars/dcff2521e0292b602f86c76fc4b5bbae.svg","isPro":false,"fullname":"XiangqiWang","user":"qisein","type":"user"},"name":"Xiangqi Wang","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:45.842Z","hidden":false},{"_id":"67b7e371f17ca6989faa9889","name":"Yujun Zhou","hidden":false},{"_id":"67b7e371f17ca6989faa988a","user":{"_id":"6512a4322f0aa026dd6dc9f8","avatarUrl":"/avatars/7cc88d2d8061a83a24bb4458d7cbb242.svg","isPro":false,"fullname":"wyf","user":"wyf23187","type":"user"},"name":"Yanbo Wang","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:54.838Z","hidden":false},{"_id":"67b7e371f17ca6989faa988b","name":"Jiayi Ye","hidden":false},{"_id":"67b7e371f17ca6989faa988c","name":"Jiawen Shi","hidden":false},{"_id":"67b7e371f17ca6989faa988d","user":{"_id":"67a99d1fef1439e285c4cbec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/VrwUmrY2wsg4sVSIMc--K.png","isPro":false,"fullname":"Qihui Zhang","user":"77Hui","type":"user"},"name":"Qihui Zhang","status":"claimed_verified","statusLastChangedAt":"2025-03-21T11:46:47.569Z","hidden":false},{"_id":"67b7e371f17ca6989faa988e","name":"Yuan Li","hidden":false},{"_id":"67b7e371f17ca6989faa988f","name":"Han Bao","hidden":false},{"_id":"67b7e371f17ca6989faa9890","name":"Zhaoyi Liu","hidden":false},{"_id":"67b7e371f17ca6989faa9891","user":{"_id":"64baeea1d1c7b6d84883e7fb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64baeea1d1c7b6d84883e7fb/gYEYt5T5ee50-dL1UbEzd.jpeg","isPro":false,"fullname":"Tianrui Guan","user":"rayguan","type":"user"},"name":"Tianrui Guan","status":"claimed_verified","statusLastChangedAt":"2025-03-31T08:16:14.619Z","hidden":false},{"_id":"67b7e371f17ca6989faa9892","name":"Dongping Chen","hidden":false},{"_id":"67b7e371f17ca6989faa9893","name":"Ruoxi Chen","hidden":false},{"_id":"67b7e371f17ca6989faa9894","name":"Kehan Guo","hidden":false},{"_id":"67b7e371f17ca6989faa9895","name":"Andy Zou","hidden":false},{"_id":"67b7e371f17ca6989faa9896","name":"Bryan Hooi Kuen-Yew","hidden":false},{"_id":"67b7e371f17ca6989faa9897","name":"Caiming Xiong","hidden":false},{"_id":"67b7e371f17ca6989faa9898","name":"Elias Stengel-Eskin","hidden":false},{"_id":"67b7e371f17ca6989faa9899","name":"Hongyang Zhang","hidden":false},{"_id":"67b7e371f17ca6989faa989a","name":"Hongzhi Yin","hidden":false},{"_id":"67b7e371f17ca6989faa989b","name":"Huan Zhang","hidden":false},{"_id":"67b7e371f17ca6989faa989c","name":"Huaxiu Yao","hidden":false},{"_id":"67b7e371f17ca6989faa989d","user":{"_id":"652066649004117947e46ed6","avatarUrl":"/avatars/972c97df6f26d2c3d6ce71ec579984bb.svg","isPro":false,"fullname":"Jaehong Yoon","user":"jaehong31","type":"user"},"name":"Jaehong Yoon","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:50.021Z","hidden":false},{"_id":"67b7e371f17ca6989faa989e","name":"Jieyu Zhang","hidden":false},{"_id":"67b7e371f17ca6989faa989f","name":"Kai Shu","hidden":false},{"_id":"67b7e371f17ca6989faa98a0","name":"Kaijie Zhu","hidden":false},{"_id":"67b7e371f17ca6989faa98a1","name":"Ranjay Krishna","hidden":false},{"_id":"67b7e371f17ca6989faa98a2","user":{"_id":"688b03af9c6feb94ac299fc9","avatarUrl":"/avatars/bf94918c198fe866a7d4056ea887108f.svg","isPro":false,"fullname":"Swabha Swayamdipta","user":"swabhs","type":"user"},"name":"Swabha Swayamdipta","status":"claimed_verified","statusLastChangedAt":"2025-07-31T08:16:50.300Z","hidden":false},{"_id":"67b7e371f17ca6989faa98a3","user":{"_id":"62e1b3cb3eb0730f621a83f6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1658958764563-noauth.jpeg","isPro":false,"fullname":"Taiwei Shi","user":"MaksimSTW","type":"user"},"name":"Taiwei Shi","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:56.645Z","hidden":false},{"_id":"67b7e371f17ca6989faa98a4","name":"Weijia Shi","hidden":false},{"_id":"67b7e371f17ca6989faa98a5","name":"Xiang Li","hidden":false},{"_id":"67b7e371f17ca6989faa98a6","name":"Yiwei Li","hidden":false},{"_id":"67b7e371f17ca6989faa98a7","name":"Yuexing Hao","hidden":false},{"_id":"67b7e371f17ca6989faa98a8","name":"Yuexing Hao","hidden":false},{"_id":"67b7e371f17ca6989faa98a9","name":"Zhihao Jia","hidden":false},{"_id":"67b7e371f17ca6989faa98aa","name":"Zhize Li","hidden":false},{"_id":"67b7e371f17ca6989faa98ab","name":"Xiuying Chen","hidden":false},{"_id":"67b7e371f17ca6989faa98ac","user":{"_id":"62548d5fef3debb2ddf91217","avatarUrl":"/avatars/14975b45568f9c399c92c3986b6ce83e.svg","isPro":false,"fullname":"Zhengzhong Tu","user":"vztu","type":"user"},"name":"Zhengzhong Tu","status":"claimed_verified","statusLastChangedAt":"2025-06-03T08:55:43.728Z","hidden":false},{"_id":"67b7e371f17ca6989faa98ad","name":"Xiyang Hu","hidden":false},{"_id":"67b7e371f17ca6989faa98ae","user":{"_id":"647f5af5b0e96764589f3b2a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/VJ4cDyjp5M3V5WmI5gPIU.jpeg","isPro":false,"fullname":"Tianyi Zhou","user":"zhoutianyi","type":"user"},"name":"Tianyi Zhou","status":"claimed_verified","statusLastChangedAt":"2025-04-17T08:05:40.535Z","hidden":false},{"_id":"67b7e371f17ca6989faa98af","name":"Jieyu Zhao","hidden":false},{"_id":"67b7e371f17ca6989faa98b0","name":"Lichao Sun","hidden":false},{"_id":"67b7e371f17ca6989faa98b1","name":"Furong Huang","hidden":false},{"_id":"67b7e371f17ca6989faa98b2","user":{"_id":"67b7eccd10a9714460d767fc","avatarUrl":"/avatars/93b03f5a9df7bab777295d811520454f.svg","isPro":false,"fullname":"Or Cohen-Sasson","user":"orcs-prime","type":"user"},"name":"Or Cohen Sasson","status":"claimed_verified","statusLastChangedAt":"2025-02-21T09:58:47.678Z","hidden":false},{"_id":"67b7e371f17ca6989faa98b3","name":"Prasanna Sattigeri","hidden":false},{"_id":"67b7e371f17ca6989faa98b4","name":"Anka Reuel","hidden":false},{"_id":"67b7e371f17ca6989faa98b5","name":"Max Lamparth","hidden":false},{"_id":"67b7e371f17ca6989faa98b6","name":"Yue Zhao","hidden":false},{"_id":"67b7e371f17ca6989faa98b7","name":"Nouha Dziri","hidden":false},{"_id":"67b7e371f17ca6989faa98b8","name":"Yu Su","hidden":false},{"_id":"67b7e371f17ca6989faa98b9","name":"Huan Sun","hidden":false},{"_id":"67b7e371f17ca6989faa98ba","name":"Heng Ji","hidden":false},{"_id":"67b7e371f17ca6989faa98bb","name":"Chaowei Xiao","hidden":false},{"_id":"67b7e371f17ca6989faa98bc","name":"Mohit Bansal","hidden":false},{"_id":"67b7e371f17ca6989faa98bd","name":"Nitesh V. Chawla","hidden":false},{"_id":"67b7e371f17ca6989faa98be","name":"Jian Pei","hidden":false},{"_id":"67b7e371f17ca6989faa98bf","name":"Jianfeng Gao","hidden":false},{"_id":"67b7e371f17ca6989faa98c0","name":"Michael Backes","hidden":false},{"_id":"67b7e371f17ca6989faa98c1","name":"Philip S. Yu","hidden":false},{"_id":"67b7e371f17ca6989faa98c2","name":"Neil Zhenqiang Gong","hidden":false},{"_id":"67b7e371f17ca6989faa98c3","name":"Pin-Yu Chen","hidden":false},{"_id":"67b7e371f17ca6989faa98c4","name":"Bo Li","hidden":false},{"_id":"67b7e371f17ca6989faa98c5","name":"Xiangliang Zhang","hidden":false}],"publishedAt":"2025-02-20T06:20:36.000Z","submittedOnDailyAt":"2025-02-20T23:55:09.725Z","title":"On the Trustworthiness of Generative Foundation Models: Guideline,\n Assessment, and Perspective","submittedOnDailyBy":{"_id":"639d94ab7145123e0d44e48a","avatarUrl":"/avatars/5bb6a65b306d1383c4a8bcd9334b470a.svg","isPro":false,"fullname":"Yue Huang","user":"HowieHwong","type":"user"},"summary":"Generative Foundation Models (GenFMs) have emerged as transformative tools.\nHowever, their widespread adoption raises critical concerns regarding\ntrustworthiness across dimensions. This paper presents a comprehensive\nframework to address these challenges through three key contributions. First,\nwe systematically review global AI governance laws and policies from\ngovernments and regulatory bodies, as well as industry practices and standards.\nBased on this analysis, we propose a set of guiding principles for GenFMs,\ndeveloped through extensive multidisciplinary collaboration that integrates\ntechnical, ethical, legal, and societal perspectives. Second, we introduce\nTrustGen, the first dynamic benchmarking platform designed to evaluate\ntrustworthiness across multiple dimensions and model types, including\ntext-to-image, large language, and vision-language models. TrustGen leverages\nmodular components--metadata curation, test case generation, and contextual\nvariation--to enable adaptive and iterative assessments, overcoming the\nlimitations of static evaluation methods. Using TrustGen, we reveal significant\nprogress in trustworthiness while identifying persistent challenges. Finally,\nwe provide an in-depth discussion of the challenges and future directions for\ntrustworthy GenFMs, which reveals the complex, evolving nature of\ntrustworthiness, highlighting the nuanced trade-offs between utility and\ntrustworthiness, and consideration for various downstream applications,\nidentifying persistent challenges and providing a strategic roadmap for future\nresearch. This work establishes a holistic framework for advancing\ntrustworthiness in GenAI, paving the way for safer and more responsible\nintegration of GenFMs into critical applications. To facilitate advancement in\nthe community, we release the toolkit for dynamic evaluation.","upvotes":44,"discussionId":"67b7e375f17ca6989faa9a28","ai_summary":"A framework is provided for enhancing the trustworthiness of Generative Foundation Models via comprehensive governance principles and the introduction of TrustGen, a benchmarking platform that evaluates trustworthiness across diverse GenFMs.","ai_keywords":["Generative Foundation Models","GenFMs","AI governance","guiding principles","multidisciplinary collaboration","TrustGen","dynamic benchmarking platform","metadata curation","test case generation","contextual variation","iterative assessments","trustworthiness","text-to-image","large language models","vision-language models","GenAI"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6467941c76bb704aa1425405","avatarUrl":"/avatars/055fda4161bee008fabeac71a7861b2c.svg","isPro":false,"fullname":"Cicinao","user":"CKIfn","type":"user"},{"_id":"6347afbb8af48bc2fb542cdd","avatarUrl":"/avatars/62f2a03fa310bd4c7a6beb219e0ace61.svg","isPro":false,"fullname":"haomin","user":"DaydreamerMZM","type":"user"},{"_id":"62e1b3cb3eb0730f621a83f6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1658958764563-noauth.jpeg","isPro":false,"fullname":"Taiwei Shi","user":"MaksimSTW","type":"user"},{"_id":"639d94ab7145123e0d44e48a","avatarUrl":"/avatars/5bb6a65b306d1383c4a8bcd9334b470a.svg","isPro":false,"fullname":"Yue Huang","user":"HowieHwong","type":"user"},{"_id":"643be8879f5d314db2d9ed23","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643be8879f5d314db2d9ed23/VrW2UtJ7ppOnGIYjTWd7b.png","isPro":false,"fullname":"Chen Dongping","user":"shuaishuaicdp","type":"user"},{"_id":"65a13cb1c5770b27aef2a2bc","avatarUrl":"/avatars/88ec5b988f10ad9fd4d469ae2fa34680.svg","isPro":false,"fullname":"Chujie Gao","user":"Flossie","type":"user"},{"_id":"64baeea1d1c7b6d84883e7fb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64baeea1d1c7b6d84883e7fb/gYEYt5T5ee50-dL1UbEzd.jpeg","isPro":false,"fullname":"Tianrui Guan","user":"rayguan","type":"user"},{"_id":"64b82c659ebb69a79f0073f6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b82c659ebb69a79f0073f6/INEHG7kijEHOhFZMjdBIM.png","isPro":false,"fullname":"Haoran Wang","user":"wang2226","type":"user"},{"_id":"65a05abf07184d32fa002d41","avatarUrl":"/avatars/3a23e7e568d2024381ed31b56c1c461a.svg","isPro":false,"fullname":"Yujun Zhou","user":"yujunzhou","type":"user"},{"_id":"64770d4f5ef58684691e4e57","avatarUrl":"/avatars/7afe56ead9b1233b027e15d0e974f6af.svg","isPro":false,"fullname":"KehanGuo","user":"kguo2","type":"user"},{"_id":"65e40e1cd4f76e7d1b34d6cf","avatarUrl":"/avatars/81e147a8c6edad5a6aebab4c9494ba1e.svg","isPro":false,"fullname":"liu","user":"handsome-face","type":"user"},{"_id":"67b7e7f7fedfe971271c18b1","avatarUrl":"/avatars/1e4db1dd62bd68e17d081e595bbd95af.svg","isPro":false,"fullname":"fgvf","user":"jerfv","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">
Papers
arxiv:2502.14296

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Published on Feb 20
· Submitted by Yue Huang on Feb 20
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

A framework is provided for enhancing the trustworthiness of Generative Foundation Models via comprehensive governance principles and the introduction of TrustGen, a benchmarking platform that evaluates trustworthiness across diverse GenFMs.

AI-generated summary

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.

Community

Paper author Paper submitter

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2502.14296 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2502.14296 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2502.14296 in a Space README.md to link it from this page.

Collections including this paper 5

Лучший частный хостинг