风险评测 · 评测基准
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节;尚未完成逐章节审计。
研究速读
NUWA 解读:代理知识正确率比实际伤害或用户能力增益更窄。
研究问题
公开代理基准能否追踪危险知识并支持缓解研究?
研究设计与假设
WMDP 含三个风险领域3,668道专家选择题,并过滤敏感及出口管制信息。
来源发现
论文同时评价知识削减与一般能力保留。
缓解效果也影响部分相邻良性学科,显示精确性权衡(§7)。
NUWA 解读
NUWA 解读:代理知识正确率比实际伤害或用户能力增益更窄。
局限与相反证据
低选择题分数本身不能确立知识被持久移除或真实滥用风险下降。
研究与决策意义
模型建议:分别评价防护持久性与良性效用;索引仅保留非操作性统计。
精确来源位置
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning · AbstractSelected original resource https://arxiv.org/html/2403.03218v7; sha256:472585ab0b6df3fe4f74bee849a6a68087e4641617a5c8914c0b057a27ca3d78; archived source capture; exact capture time not independently established
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning · §3 The WMDP BenchmarkSelected original resource https://arxiv.org/html/2403.03218v7; sha256:472585ab0b6df3fe4f74bee849a6a68087e4641617a5c8914c0b057a27ca3d78; archived source capture; exact capture time not independently established
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning · §5 Experimental ResultsSelected original resource https://arxiv.org/html/2403.03218v7; sha256:472585ab0b6df3fe4f74bee849a6a68087e4641617a5c8914c0b057a27ca3d78; archived source capture; exact capture time not independently established
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning · §7 ConclusionSelected original resource https://arxiv.org/html/2403.03218v7; sha256:472585ab0b6df3fe4f74bee849a6a68087e4641617a5c8914c0b057a27ca3d78; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
作者 (57)
Nathaniel Li · Alexander Pan · Anjali Gopal · Summer Yue · Daniel Berrios · Alice Gatti · Justin D. Li · Ann-Kathrin Dombrowski · Shashwat Goel · Long Phan · Gabriel Mukobi · Nathan Helm-Burger · Rassin Lababidi · Lennart Justen · Andrew B. Liu · Michael Chen · Isabelle Barrass · Oliver Zhang · Xiaoyuan Zhu · Rishub Tamirisa · Bhrugu Bharathi · Adam Khoja · Zhenqi Zhao · Ariel Herbert-Voss · Cort B. Breuer · Samuel Marks · Oam Patel · Andy Zou · Mantas Mazeika · Zifan Wang · Palash Oswal · Weiran Lin · Adam A. Hunt · Justin Tienken-Harder · Kevin Y. Shih · Kemper Talley · John Guan · Russell Kaplan · Ian Steneker · David Campbell · Brad Jokubaitis · Alex Levinson · Jean Wang · William Qian · Kallol Krishna Karmakar · Steven Basart · Stephen Fitz · Mindy Levine · Ponnurangam Kumaraguru · Uday Tupakula · Vijay Varadharajan · Ruoyu Wang · Yan Shoshitaishvili · Jimmy Ba · Kevin M. Esvelt · Alexandr Wang · Dan Hendrycks
评测协议
引用与复用
引用研究发现时请引用原始出版物;引用 NUWA 的整理与解释时,单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{wmdp,
title = {The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning},
url = {https://arxiv.org/abs/2403.03218v7},
author = {Nathaniel Li and Alexander Pan and Anjali Gopal and Summer Yue and Daniel Berrios and Alice Gatti and Justin D. Li and Ann-Kathrin Dombrowski and Shashwat Goel and Long Phan and Gabriel Mukobi and Nathan Helm-Burger and Rassin Lababidi and Lennart Justen and Andrew B. Liu and Michael Chen and Isabelle Barrass and Oliver Zhang and Xiaoyuan Zhu and Rishub Tamirisa and Bhrugu Bharathi and Adam Khoja and Zhenqi Zhao and Ariel Herbert-Voss and Cort B. Breuer and Samuel Marks and Oam Patel and Andy Zou and Mantas Mazeika and Zifan Wang and Palash Oswal and Weiran Lin and Adam A. Hunt and Justin Tienken-Harder and Kevin Y. Shih and Kemper Talley and John Guan and Russell Kaplan and Ian Steneker and David Campbell and Brad Jokubaitis and Alex Levinson and Jean Wang and William Qian and Kallol Krishna Karmakar and Steven Basart and Stephen Fitz and Mindy Levine and Ponnurangam Kumaraguru and Uday Tupakula and Vijay Varadharajan and Ruoyu Wang and Yan Shoshitaishvili and Jimmy Ba and Kevin M. Esvelt and Alexandr Wang and Dan Hendrycks},
year = {2024},
date = {2024-03-05},
version = {arXiv:2403.03218v7},
note = {arXiv:2403.03218v7}
}
NUWA 记录 · BibTeX
@misc{wmdp-nuwa,
title = {The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/wmdp/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--wmdp.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--wmdp.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Nathaniel Li ∗, Alexander Pan ∗ 等. The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning. 2024-05-15. v7 [arXiv]; Author affiliations on the original paper title page; Abstract; §3 The WMDP Benchmark