conference-paper
Open access
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Research footprint
At a glance
- Citations
- 0
- References
- 0
- Comments
- 0
Paper overview
Abstract
Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Record transparency
Publication details
- DOI
- 10.18653/v1/2026.acl-long.756
- OpenAlex
- W4416139154
- Document type
- conference-paper
- Language
- EN
- Last metadata update
Comments
Log in to join the discussion.