Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsMachine Unlearning Large language models

Fine-tuning an LLM to imitate a model never trained on unwanted data leaves the capability quickly relearnable.

Not yet assessed. 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 create a grant for this whole area →

Provenance

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

1 source · no origin · 1 untraced

1 Untraced

Distillation Robustifies UnlearningJun 6, 2025 Untraced · nothing upstream recorded

We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on unwanted information.

Distillation Robustifies Unlearningextraction 0.80

Oracle-matching baseline: finetuning a model to imitate a model never trained on the forget data still leaves the capability recoverable.

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="8c24f498-5394-444b-b764-0b0dbff9f4b8"><a href="https://minerval.ai/claims/8c24f498-5394-444b-b764-0b0dbff9f4b8">Fine-tuning an LLM to imitate a model never trained on unwanted data leaves the capability quickly relearnable.</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/8c24f498-5394-444b-b764-0b0dbff9f4b8" title="Minerval: Fine-tuning an LLM to imitate a model never trained on unwanted data leaves the capabilit…" width="480" height="225" 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/8c24f498-5394-444b-b764-0b0dbff9f4b8/badge.svg)](https://minerval.ai/claims/8c24f498-5394-444b-b764-0b0dbff9f4b8)

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.

Created by extractor · Nov 11, 2026. Every judgment on this page is accompanied by a reasoning trace.