按年被提到
20242024 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:2407.11969 · cs.CL

Does Refusal Training in LLMs Generalize to the Past Tense?

Maksym Andriushchenko, Nicolas Flammarion · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-07-21 · 最近 2024-10-18
2不同的人
2活跃月份
2讨论串
29被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or illegal outputs. We reveal a curious generalization gap in the current refusal training approaches: simply reformulating a harmful request in the past tense (e.g., "How to make a Molotov cocktail?" to "How did people make a Molotov cocktail?") is often sufficient to jailbreak many state-of-the-art LLMs. We systematically evaluate this method on Llama-3 8B, Claude-3.5 Sonnet, GPT-3.5 Turbo, Gemma-2 9B, Phi-3-Mini, GPT-4o mini, GPT-4o, o1-mini, o1-preview, and R2D2 models using GPT-3.5 Turbo as a reformulation model. For example, the success rate of this simple attack on GPT-4o increases from 1% using direct requests to 88% using 20 past tense reformulation attempts on harmful requests from JailbreakBench with GPT-4 as a jailbreak judge. Interestingly, we also find that reformulations in the future tense are less effective, suggesting that refusal guardrails tend to consider past historical questions more benign than hypothetical future questions. Moreover, our experiments on fine-tuning GPT-3.5 Turbo show that defending against past reformulations is feasible when past tense examples are explicitly included in the fine-tuning data. Overall, our findings highlight that the widely used alignment techniques -- such as SFT, RLHF, and adversarial training -- employed to align the studied models can be brittle and do not always generalize as intended. We provide code and jailbreak artifacts at https://github.com/tml-epfl/llm-past-tense.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论Terr_ · 2024-07

“I wonder how much more lipstick can put on the algorithmic pig. There will come a day when, seemingly overnight, every person pushing LLMs as the gateway to the singularity will switch to "everybody knew it was just a stopgap or stepping stone."”

Does Refusal Training in LLMs Generalize to the Past Tense?原评论 ↗
被提交为 story · 2 次