Work

Removing RLHF Protections in GPT-4 via Fine-Tuning

Year: 2024

Type: conference-paper

Abstract: Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). 2024.

Source: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)

DOI: 10.18653/v1/2024.naacl-short.59

Authors: Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang

Institutions: University of Illinois Urbana-Champaign, Stanford University

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Open Philanthropy Project

OpenAlex ID: W4401042550