Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · notableImportance 0.55, 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 →

TopicsModel Backdoor Attacks Large language models

Backdoored LLM model organisms built with common techniques often lose their misbehavior under untargeted fine-tuning.

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

Advice for making robust-to-training model organisms Untraced · nothing upstream recorded

However, model organisms built with common techniques are often fragile: we (and other researchers like Roger et al. and Ryd et al.) have observed them to stop misbehaving after untargeted training—training that doesn’t directly target the misbehavior.

Advice for making robust-to-training model organismsextraction 0.85

Opening motivation; examples include replications of Hubinger et al., Greenblatt et al., Ryd et al. defeated by pirate-style SFT.

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="699a0579-793b-4c46-8941-9474d35ab8f7"><a href="https://minerval.ai/claims/699a0579-793b-4c46-8941-9474d35ab8f7">Backdoored LLM model organisms built with common techniques often lose their misbehavior under untargeted fine-tuning.</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/699a0579-793b-4c46-8941-9474d35ab8f7" title="Minerval: Backdoored LLM model organisms built with common techniques often lose their misbehavior…" 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/699a0579-793b-4c46-8941-9474d35ab8f7/badge.svg)](https://minerval.ai/claims/699a0579-793b-4c46-8941-9474d35ab8f7)

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.