按年被提到
20232023 · 2 次2026
大模型与语言模型›大模型文本、写作与版权·arXiv:2310.02238 · cs.CL

Who's Harry Potter? Approximate Unlearning in LLMs

Ronen Eldan, Mark Russinovich · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2023-10-22 · 最近 2024-04-25
3不同的人
2活跃月份
3讨论串
110被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) are trained on massive internet corpora that often contain copyrighted content. This poses legal and ethical challenges for the developers and users of these models, as well as the original authors and publishers. In this paper, we propose a novel technique for unlearning a subset of the training data from a LLM, without having to retrain it from scratch. We evaluate our technique on the task of unlearning the Harry Potter books from the Llama2-7b model (a generative language model recently open-sourced by Meta). While the model took over 184K GPU-hours to pretrain, we show that in about 1 GPU hour of finetuning, we effectively erase the model's ability to generate or recall Harry Potter-related content, while its performance on common benchmarks (such as Winogrande, Hellaswag, arc, boolq and piqa) remains almost unaffected. We make our fine-tuned model publicly available on HuggingFace for community evaluation. To the best of our knowledge, this is the first paper to present an effective technique for unlearning in generative language models. Our technique consists of three main components: First, we use a reinforced model that is further trained on the target data to identify the tokens that are most related to the unlearning target, by comparing its logits with those of a baseline model. Second, we replace idiosyncratic expressions in the target data with generic counterparts, and leverage the model's own predictions to generate alternative labels for every token. These labels aim to approximate the next-token predictions of a model that has not been trained on the target data. Third, we finetune the model on these alternative labels, which effectively erases the original text from the model's memory whenever it is prompted with its context.

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
评论andy99 · 2024-04

“There was one where they tried to remove Harry Potter... Who's Harry Potter? Approximate Unlearning in LLMs https://arxiv.org/abs/2310.02238 See also The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported https://arxiv.org/abs/2403.12082v1”

The "it" in AI models is the dataset原评论 ↗
被提交为 story · 2 次