Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis.
Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang
Browse the full EMNLP paper archive.
Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang
Browse the full EMNLP paper archive.