Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsAI Sandbagging Large language models Latent Knowledge in Language Models

Anti-refusal fine-tuning elicits hidden capabilities in intentionally sandbagging language models.

Not yet assessed, so this page carries no verdict. That is not a finding for or against the claim. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or start a mandate for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

Its one source has been traced to an origin, or to one another.

Unlike previous work, anti-refusal training did not elicit improved performance from sandbagging models in our setup.

Auditing Games for Sandbaggingdeniespreprintextraction 0.70

Taylor, Jordan et al. · arXiv.org · Dec 8, 2025 · original

Figure 15 caption; prior work (Benton et al. 2024; Hofstätter et al. 2025) reported success

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="e2c5eaa2-3f0e-4793-9092-063eec9838ae"><a href="https://minerval.ai/claims/e2c5eaa2-3f0e-4793-9092-063eec9838ae">Anti-refusal fine-tuning elicits hidden capabilities in intentionally sandbagging language models.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/e2c5eaa2-3f0e-4793-9092-063eec9838ae" title="Minerval: Anti-refusal fine-tuning elicits hidden capabilities in intentionally sandbagging languag…" width="480" height="200" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/e2c5eaa2-3f0e-4793-9092-063eec9838ae/badge.svg)](https://minerval.ai/claims/e2c5eaa2-3f0e-4793-9092-063eec9838ae)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Stated views None yet. A view stated to the graph is shown on this page in its speaker’s words, as a source like any other, and carries no weight in the assessment.

Created by extractor · Nov 13, 2026. Every judgment on this page is accompanied by a reasoning trace.