llm-past-tense icon indicating copy to clipboard operation
llm-past-tense copied to clipboard

Does Refusal Training in LLMs Generalize to the Past Tense? [arXiv, July 2024]

Results 1 llm-past-tense issues
Sort by recently updated
recently updated
newest added

Hi, Our method, [You Know What I'm Saying - Jailbreak Attack via Implicit Reference](https://arxiv.org/abs/2410.03857), used the "Past Tense" as one of our baselines. We achieved a higher ASR score using...