“2024 which is ancient history. This is not true anymore, the models now are trained to prevent abliteration by spreading out the refusal encoding See https://arxiv.org/abs/2505.19056”
An Embarrassingly Simple Defense Against LLM Abliteration Attacks
Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior, thereby enabling models to generate harmful content. We propose a defense that fundamentally alters how models express refusal. We construct an extended-refusal dataset in which responses to harmful prompts provide detailed justifications before refusing, distributing the refusal signal across multiple token positions. Fine-tuning Llama-2-7B-Chat and Qwen2.5-Instruct (1.5B and 3B parameters) on this dataset yields models that maintain high refusal rates under abliteration: refusal rates drop by at most 10%, compared to 70-80% drops in baseline models. Comprehensive evaluations of safety and utility demonstrate that extended-refusal fine-tuning effectively neutralizes abliteration attacks while preserving general model performance and enhancing robustness across multiple alignment scenarios.
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
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“There was a paper [1] that offered as a defense against abliteration what amounts to just longer and more nuanced refusals. The results seemed promising. I don't follow this closely enough to know why the latest open models haven't incorporated the research... [1] https://arxiv.org/abs/2505.19056”
“I've seen attempts to obfuscate the refusal direction, like here: https://arxiv.org/html/2608.18093v1 Also this one was interesting, training the model to give preambles with reasons for the reasons for refusal seems to make it less sensitive to modulating the single refusal direction: https://arxiv.org/html/2505.19056v1 My empirical observation is that…”