[2605.28839] One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
[Submitted on 18 Apr 2026]
Title:One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
View a PDF of the paper titled One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them, by Ali Holmov and 3 other authors
View PDF HTML (experimental)
Abstract:Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether edits rely on a common mechanism, regardless of which fact is modified. Despite fact-specific weight changes, we argue that ROME and MEMIT target the same subset of weights critical for maintaining edits. To isolate this subset, we train a compact binary mask over the edited weights. The mask reverses 80% of edits on the training set and over 70% on the test set, confirming that diverse edits share a common functional structure. Our analysis reveals that the mask reverses edits by eliminating overattention in later layers. Additionally, we show that injecting the mask during editing drops editing success from 98% to 38%, demonstrating that this mechanism is necessary for edits to succeed. Our finding that edits suppress rather than overwrite knowledge explains why ROME and MEMIT fail to propagate changes to related facts. The identified common functional subspace informs detection and defense against unwanted edits.
Comments: Accepted to Findings of ACL 2026
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2605.28839 [cs.LG]
(or arXiv:2605.28839v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.28839
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ali Holmov [view email] [v1] Sat, 18 Apr 2026 16:18:08 UTC (1,244 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them, by Ali Holmov and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
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?)
IArxiv recommender toggle
IArxiv Recommender (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 for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)