arXiv cs.AI· Alex Lin Wang, Linus Yifeng Tang, Dami Choi, Neil Chowdhury·· 10 小时前AI 评分49
训练语言模型实现内省式监督
Training Language Models for Introspective Oversight
AI 导读
研究者提出“内省式监督”,在模型中新增独立的第三人称观察者角色,专门回答关于助手行为的问题,并按与助手实际行为核验的结果给予奖励。基于 Qwen3.6-27B 训练的观察者在五项留出监督评测上取得平均 AUROC 0.907,优于诚实性训练(0.864)、对话记录监控(0.828)和激活探针(0.796)。训练观察者还让助手本身更易被监控,各基线方法在微调后的助手上平均表现均有提升。
正文 · 原文
Abstract:Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models are generally not trained to report their own misbehavior. As a result, approaches to oversight typically involve querying external models. These face limitations: external transcript monitoring operates only on visible model outputs, and activation decoders lack full context and are prone to confabulation. We introduce introspective oversight, which trains a new role in the model to answer arbitrary questions about the assistant, rewarding answers that are verified against the assistant's actual behavior. We implement this by adding a separate, third-person observer role that answers these queries, which we can train solely for accuracy and separately from the assistant. On five held-out oversight evaluations, an observer trained on Qwen3.6-27B obtains a mean AUROC of 0.907, outperforming honesty training (0.864), transcript monitoring (0.828), and activation oracles (0.796). We further find that training an observer makes the assistant itself easier to monitor, with every baseline method improving on average when applied to the fine-tuned assistant. These results suggest that training models to answer verifiable questions about themselves is a tractable approach to overseeing unintended behavior.
| Comments: | 31 pages, 13 figures, 8 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23365 [cs.AI] |
| (or arXiv:2611.23365v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23365 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Neil Chowdhury [view email]
[v1]
Tue, 17 Nov 2026 18:59:07 UTC (4,023 KB)
来源:arXiv cs.AI · arxiv.org