Newshot

Training Language Models for Introspective Oversight

Summary

arXiv:2611.23365v1 Announce Type: new 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, a…

Original text(via arXiv cs.AI)

Computer Science > Artificial Intelligence

Title:Training Language Models for Introspective Oversight

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

Access Paper:

  • HTML (experimental)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.AI
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗