PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
A common hypothesis in LLM modular design is that adapter interference arises from linear parameter overlap. This study tests it using DoRA-RBAC, finding that geometry-aware merging offers no consistent advantage over standard averaging, and orthogonality is a weak predictor, suggesting interference stems from shared nonlinear representations.
[2606.11262] PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
[Submitted on 9 Jun 2026]
Title:PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
View a PDF of the paper titled PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry, by Gowtham Sivaramakrishnan and Sarvesha Kumar Kombaiah Seetha and Kishan Gupta Balaji and Santhosh Baradwaj Vaduvur Ranganathan
View PDF HTML (experimental)
Abstract:Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates, suggesting that enforcing orthogonality or directional independence should improve multi-domain performance. We test this hypothesis using DoRA-RBAC, a hierarchical adapter composition framework based on weight-decomposed low-rank adaptation. We compare conventional Euclidean merging with a geometry-aware Riemannian-inspired merging strategy that approximates the Frechet mean via normalized directional averaging across multiple QA benchmarks (GPQA, PubMedQA, SimpleQA, WMDP) on LLaMA-3.1-8B and Mistral-7B. Our results show that while single-domain performance matches LoRA, geometry-aware merging provides no consistent advantage over standard averaging in multi-domain this http URL analysis further reveals that angular alignment and orthogonality of adapter updates are weak predictors of composition performance. These findings suggest that adapter interference is not governed primarily by parameter-space geometry, but is instead consistent with interactions in shared nonlinear representations.
Comments: 18 Pages, COLM 2026
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.11262 [cs.LG]
(or arXiv:2606.11262v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.11262
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Kishan Gupta Balaji [view email] [v1] Tue, 9 Jun 2026 02:52:48 UTC (32 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry, by Gowtham Sivaramakrishnan and Sarvesha Kumar Kombaiah Seetha and Kishan Gupta Balaji and Santhosh Baradwaj Vaduvur Ranganathan
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-06
Change to browse by:
cs cs.AI
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?)