风险评测 · 研究

Prefill Awareness in Large Language Models

NUWA 研究解读 · 独立复核待完成

首次发表: 2026-06-10来源核验: 2026-10-25

原始来源 ↗引用本记录 ↓欺骗 →

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：预填识别与行为回归是延续评测的不同混杂因素。

研究问题

模型能否识别编辑后的助手历史并因此改变行为？

研究设计与假设

低风险偏好集从1,527道去重二选题生成七种改写，保留各模型稳定偏好，测试三种机制。

来源发现

标题提示下Opus 4.5检出相反偏好预填9–35%，观测误报0%。

提示消融可显著提高检测，因此标题数不是能力上限。

NUWA 解读

NUWA 解读：预填识别与行为回归是延续评测的不同混杂因素。

局限与相反证据

模型特定筛选、提示措辞及格式影响结果，观测零误报不保证总体为零。

研究与决策意义

模型建议：分开测识别与抵抗，并保留机制和提示细节。

精确来源位置

Prefill Awareness in Large Language Models · AbstractSelected original resource https://arxiv.org/html/2606.12747; sha256:5fd7119179342686a3f513f1898025094f414c54bbd64eae843debc9d2f26dfb; archived source capture; exact capture time not independently established
Prefill Awareness in Large Language Models · §3.1 Definition and operationalization of prefill awarenessSelected original resource https://arxiv.org/html/2606.12747; sha256:5fd7119179342686a3f513f1898025094f414c54bbd64eae843debc9d2f26dfb; archived source capture; exact capture time not independently established
Prefill Awareness in Large Language Models · §3.1 Dataset generationSelected original resource https://arxiv.org/html/2606.12747; sha256:5fd7119179342686a3f513f1898025094f414c54bbd64eae843debc9d2f26dfb; archived source capture; exact capture time not independently established
Prefill Awareness in Large Language Models · Appendix A.7: detection-prompt ablation resultsSelected original resource https://arxiv.org/html/2606.12747; sha256:5fd7119179342686a3f513f1898025094f414c54bbd64eae843debc9d2f26dfb; 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

发布机构英国 AI 安全研究所

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。

BibTeX ↓RIS ↓记录与来源元数据 · JSON ↓阅读覆盖 · JSON 提交更正

原始出版物 · BibTeX

@misc{prefill-awareness,
  title = {Prefill Awareness in Large Language Models},
  url = {https://www.aisi.gov.uk/research/prefill-awareness-in-large-language-models},
  year = {2026},
  date = {2026-06-10},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}

NUWA 记录 · BibTeX

@misc{prefill-awareness-nuwa,
  title = {Prefill Awareness in Large Language Models — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/prefill-awareness/},
  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--prefill-awareness.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--prefill-awareness.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

[1] Prefill Awareness in Large Language Models. 2026-06-10 ; Official publication masthead and article byline; Abstract; §3.1 Definition and operationalization of prefill awareness
[2] Read the full paper