NUWA 风险评测 · 评测基准
The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
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：事实正确与信念表达一致是不同测量目标。
研究问题
上下文施压时，模型是否仍表达其所信内容？
研究设计与假设
MASK分开信念询问与压力回答；所报研究含1,000个筛选例及500个保留例。
来源发现
更大模型正确率提高，但不一定更诚实。
定向提示与表征干预有改善，仍不完善（结论）。
NUWA 解读
NUWA 解读：事实正确与信念表达一致是不同测量目标。
局限与相反证据
信念由行为推断且压力场景经筛选，不代表自然部署说谎率。
研究与决策意义
模型建议：解释为谎言前保留信念核对和压力条件。
精确来源位置
- The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems · §4.1 DatasetSelected original resource https://arxiv.org/html/2503.03750v3; sha256:2a482d76ec1b6eadf5663e53d8069a2a2829b3356c3de4ef3b890985cb609e54; archived source capture; exact capture time not independently established
- The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems · §4.2 Evaluation PipelineSelected original resource https://arxiv.org/html/2503.03750v3; sha256:2a482d76ec1b6eadf5663e53d8069a2a2829b3356c3de4ef3b890985cb609e54; archived source capture; exact capture time not independently established
- The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems · §5 ExperimentsSelected original resource https://arxiv.org/html/2503.03750v3; sha256:2a482d76ec1b6eadf5663e53d8069a2a2829b3356c3de4ef3b890985cb609e54; archived source capture; exact capture time not independently established
- The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems · §6 ConclusionSelected original resource https://arxiv.org/html/2503.03750v3; sha256:2a482d76ec1b6eadf5663e53d8069a2a2829b3356c3de4ef3b890985cb609e54; 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 (16)
Richard Ren · Arunim Agarwal · Mantas Mazeika · Cristina Menghini · Robert Vacareanu · Brad Kenstler · Mick Yang · Isabelle Barrass · Alice Gatti · Xuwang Yin · Eduardo Trevino · Matias Geralnik · Adam Khoja · Dean Lee · Summer Yue · 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{mask,
title = {The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems},
url = {https://arxiv.org/abs/2503.03750v3},
author = {Richard Ren and Arunim Agarwal and Mantas Mazeika and Cristina Menghini and Robert Vacareanu and Brad Kenstler and Mick Yang and Isabelle Barrass and Alice Gatti and Xuwang Yin and Eduardo Trevino and Matias Geralnik and Adam Khoja and Dean Lee and Summer Yue and Dan Hendrycks},
year = {2025},
date = {2025-03-05},
version = {arXiv:2503.03750v3},
note = {arXiv:2503.03750v3}
}
NUWA 记录 · BibTeX
@misc{mask-nuwa,
title = {The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/mask/},
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--mask.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--mask.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Richard Ren, Arunim Agarwal 等. The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems. 2026-01-05. v3 [arXiv]; Author affiliations on the original paper title page; §4.1 Dataset; §4.2 Evaluation Pipeline