From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

20 March 2024

Papers citing "From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards"

7 / 7 papers shown

Title
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset Khaoula Chehbouni Jonathan Colaço-Carr Yash More Jackie CK Cheung G. Farnadi 117 1 0 12 Nov 2024
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation Xinpeng Wang Chengzhi Hu Paul Röttger Barbara Plank 92 9 0 04 Oct 2024
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models Wei Ping Weixin Chen Hengzhi Pei Chulin Xie Mintong Kang ... Zinan Lin Yuk-Kit Cheng Sanmi Koyejo D. Song Yue Liu 38 405 0 20 Jun 2023
Red Teaming Language Models with Language Models Ethan Perez Saffron Huang Francis Song Trevor Cai Roman Ring John Aslanides Amelia Glaese Nat McAleese G. Irving AAML 29 627 0 07 Feb 2022
Ethical and social risks of harm from Language Models Laura Weidinger John F. J. Mellor Maribeth Rauh Conor Griffin J. Uesato ... Lisa Anne Hendricks William S. Isaac Sean Legassick G. Irving Iason Gabriel PILM 56 1,009 0 08 Dec 2021
Persistent Anti-Muslim Bias in Large Language Models Abubakar Abid Maheen Farooqi James Zou AILaw 63 545 0 14 Jan 2021
Language (Technology) is Power: A Critical Survey of "Bias" in NLP Su Lin Blodgett Solon Barocas Hal Daumé Hanna M. Wallach 77 1,211 0 28 May 2020