Skip to content
AI News HubLIVE
Original source2 min read

LoRAWeaver: Directional Adapter Routing in LoRA Representation Space

Summary

This paper introduces LoRAWeaver, a training-free adapter routing method that treats adapter selection as a representation alignment problem in the adapter-output space, matching adapter-conditioned query representations against task prototypes via cosine similarity. Experiments with LLaMA-2-7B and LLaMA-2-13B on a 48-task FLAN-v2 benchmark and out-of-distribution tasks show it outperforms training-free baselines and approaches a trained retrieval encoder without learning a router.

SourcearXiv AIAuthor: Inish Melroy D Souza, Tom Jackson, Vitor Castro, Rebecca Higginson, Andrea Soltoggio
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:LoRAWeaver: Directional Adapter Routing in LoRA Representation Space

View a PDF of the paper titled LoRAWeaver: Directional Adapter Routing in LoRA Representation Space, by Inish Melroy D Souza and 4 other authors

View PDF HTML (experimental)

Abstract:Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complicates adapter selection during inference. Existing routing and encoder-based methods often require retraining when new adapters are added, which limits their use in dynamic settings. This paper treats adapter routing as a representation alignment problem in the adapter-output space. The proposed training-free method selects adapters by matching adapter-conditioned query representations against task prototypes using cosine similarity. Experiments with LLaMA-2-7B and LLaMA-2-13B on a 48-task FLAN-v2 benchmark and on out-of-distribution tasks show that the method outperforms training-free baselines in the cross-task setting and approaches a trained retrieval encoder without learning a router. An ablation confirms the benefit of directional alignment in the adapter-output space.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.17340 [cs.AI]

(or arXiv:2611.17340v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.17340

arXiv-issued DOI via DataCite

Submission history

From: Inish Melroy D Souza [view email] [v1] Tue, 1 Sep 2026 01:33:50 UTC (492 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled LoRAWeaver: Directional Adapter Routing in LoRA Representation Space, by Inish Melroy D Souza and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Formulates adapter routing as a representation alignment problem in the adapter-output space, enabling dynamic adapter selection without training a router.
  • Evaluated on LLaMA-2-7B and LLaMA-2-13B across a 48-task FLAN-v2 benchmark, outperforming training-free baselines in cross-task settings.
  • Approaches the performance of a trained retrieval encoder without requiring any router training, making it suitable for dynamic adapter pools.
  • Ablation studies confirm the benefit of directional alignment in the adapter-output space.

Highlights and analysis are generated automatically and may contain errors. Check the original source.