Tianyu Pang

Featured in: Favicon

rebellionresearch.com

Articles

[2501.17858] Improving Your Model Ranking on Chatbot Arena by Vote Rigging

2 months ago | arxiv.org | Tianyu Pang |Chao Du |Qian Liu |Minhao Cheng

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Oct 9, 2024 | arxiv.org | Tianyu Pang |Chao Du |Qian Liu |Jing Jiang
[2406.01288] Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Jun 3, 2024 | arxiv.org | Tianyu Pang |Chao Du |Qian Liu |Jing Jiang
[2302.04638] Better Diffusion Models Further Improve Adversarial Training

Jun 1, 2023 | arxiv.org | Tianyu Pang |Chao Du |Min Lin |Weiwei Liu

arXiv:2302.04638 (cs) [Submitted on 9 Feb 2023 (v1), last revised 1 Jun 2023 (this version, v2)] Download a PDF of the paper titled Better Diffusion Models Further Improve Adversarial Training, by Zekai Wang and 5 other authors Download PDF Submission history From: Tianyu Pang [ view email] [v1] Thu, 9 Feb 2023 13:46:42 UTC (693 KB) [v2] Thu, 1 Jun 2023 10:23:16 UTC (696 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?)...