Home/Author

Daniel D. Kang

3 works· latest 2025· 1 institutionscluster: provisionalORCID 0000-0001-9860-9938

h-index3

i102

Citations45

Works here3

Most cited in this library

Removing RLHF Protections in GPT-4 via Fine-Tuning2024 · 26 citations
A Safe Harbor for AI Evaluation and Red Teaming2024 · 13 citations
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?2025 · 6 citations

Works

3 shown

REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?

Findings of the Association for Computational Linguistics: ACL (Findings of ACL)·2025·3 authors·other·Open access

6citations

A Safe Harbor for AI Evaluation and Red Teaming

arXiv (Cornell University)·2024·23 authors·preprint·Open access

13citations

Removing RLHF Protections in GPT-4 via Fine-Tuning

Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)·2024·5 authors·other·Open access

26citations