[2605.25902] Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
-->
Computer Science > Machine Learning
arXiv:2605.25902 (cs)
[Submitted on 25 May 2026]
Title:Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
Authors:Michał Brzozowski, Zuzanna Dubanowska, Enrico Cassano, Neo Christopher Chung<br>View a PDF of the paper titled Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing, by Micha{\l} Brzozowski and 3 other authors
View PDF<br>HTML (experimental)
Abstract:Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weights or training data, remains an open challenge. Recent work shows that activation differences between base and finetuned models carry readable traces of the finetuning domain; the state-of-the-art Activation Difference Lens (ADL) recovers a vague domain-level description but requires full "white-box" access to model internals. We introduce Contrastive Decoding Diffing (CDD), a model diffing method that operates on output-level logit distributions only, with no weight access, no layer selection, and no per-model tuning, yet recovers implanted facts. CDD consists of three ideas: bypassing the chat template to expose the raw finetuning prior, seeding generation with maximally vague pre-fills, and amplifying the logit-space difference between finetuned and base models at each decoding step. A single default configuration recovers implanted facts verbatim -- exact drug names, vote counts, physical measurements, and procedural details -- across four architectures (1B--32B parameters), uniformly outperforming ADL despite less access and running ~170x faster. Furthermore, CDD surfaces unintended data pipeline artifacts: a fictional persona introduced by the LLM data generator via mode collapse leaked into model weights and was extracted by CDD, constituting to our knowledge the first demonstrated end-to-end fingerprinting chain from data generator artifact to model weights to recovered output. We validate on real-domain finetuning settings, achieving near-perfect recovery across all single-dataset non-CoT variants and correctly identifying all four datasets in the mixed-dataset setting. CDD's success as a grey-box method outperforming white-box baselines underscores its practical utility for transparency and accountability in AI systems.
Subjects:
Machine Learning (cs.LG)
Cite as:<br>arXiv:2605.25902 [cs.LG]
(or<br>arXiv:2605.25902v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.25902
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Michał Brzozowski [view email]<br>[v1]<br>Mon, 25 May 2026 14:29:36 UTC (829 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing, by Micha{\l} Brzozowski and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.LG
next >
new<br>recent<br>| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
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?)
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?)
IArxiv recommender toggle
IArxiv Recommender<br>(What is IArxiv?)
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...