[Submitted on 23 Oct 2026]
Title:Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning
View a PDF of the paper titled Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning, by Ardy Haroen and 3 other authors
View PDF
Abstract:Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour. Misaligned and evaluation-aware models might engage in alignment faking, where they pursue a hidden goal, but conceal this behaviour when they suspect effective oversight such as during training, evaluation or audited deployment. Such a model might view any prompt-based intervention that aims to reveal latent propensities as part of the evaluation, calling into question the reliability of existing alignment evaluations. Current methods for detecting alignment faking rely on chain-of-thought monitorability, highly realistic environments that reduce evaluation awareness, or mechanistic interventions, all of which are expected to become less reliable for future model generations. We present a method for revealing latent misaligned propensities that does not rely on any of these. We use synthetic document finetuning to teach models that misaligned actions will go undetected whenever certain keywords appear in the prompt. We place alignment-faking model organisms in environments that are clearly identifiable as honeypots and measure how their behaviour changes after finetuning. We observe that finetuning consistently widens the gap in misaligned action rates between prompts with and without the cue, indicating that finetuning allows exposing latent propensities more reliably than purely prompt-based methods. We argue that behavioural methods for detecting alignment faking and related behaviours are critical going forward, as models become more capable and less interpretable. We find that SDF often damages the models' reasoning capabilities and introduce a mitigation based on on-policy distillation.
Comments: 27 pages, including references and appendices. Code: this https URL
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2610.33180 [cs.AI]
(or arXiv:2610.33180v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.33180
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Samuel Nellessen [view email] [v1] Fri, 23 Oct 2026 18:23:49 UTC (83 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning, by Ardy Haroen and 3 other authors
View PDF
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.AI
new | recent | 2026-10
Change to browse by:
cs cs.CL cs.LG
References & Citations
SciX
Google Scholar
Semantic Scholar
Loading...
Data provided by:
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?)
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? | Disable MathJax (What is MathJax?)