[2601.10160] Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment

-->

Computer Science > Computation and Language

arXiv:2601.10160 (cs)

[Submitted on 15 Jan 2026 (v1), last revised 19 Feb 2026 (this version, v2)]

Title:Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment

Authors:Cameron Tice, Puria Radmard, Samuel Ratnam, Andy Kim, David Africa, Kyle O'Brien<br>View a PDF of the paper titled Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment, by Cameron Tice and 5 other authors

View PDF<br>HTML (experimental)

Abstract:Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may internalise corresponding behavioural priors, giving rise to self-fulfilling misalignment. This paper provides the first controlled study of this hypothesis by pretraining 6.9B-parameter LLMs with varying amounts of (mis)alignment discourse. We find that discussion of AI contributes to misalignment. Upsampling synthetic training documents about AI misalignment leads to a notable increase in misaligned behaviour. Conversely, upsampling documents about aligned behaviour reduces misalignment scores from 45% to 9%. We consider this evidence of self-fulfilling alignment. These effects are dampened, but persist through post-training. Our findings establish the study of how pretraining data shapes alignment priors, or alignment pretraining, as a complement to post-training. We recommend practitioners consider pretraining for alignment alongside capabilities. We share our models, data, and evaluations at this http URL.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:<br>arXiv:2601.10160 [cs.CL]

(or<br>arXiv:2601.10160v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2601.10160

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Kyle O'Brien [view email]<br>[v1]<br>Thu, 15 Jan 2026 07:59:31 UTC (1,982 KB)

[v2]<br>Thu, 19 Feb 2026 22:53:56 UTC (2,369 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment, by Cameron Tice and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context: cs.CL

next >

new<br>recent<br>| 2026-01

Change to browse by:

cs<br>cs.AI<br>cs.LG

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

Links to Code Toggle

Papers with Code (What is Papers with Code?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

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 .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)