Papers
arxiv:2601.16390

Cross-Lingual Activation Steering for Multilingual Language Models

Published on Jan 23
Authors:
,
,

Abstract

Cross-Lingual Activation Steering enables targeted modulation of neuron activations to improve multilingual model performance without changing model weights.

Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work attributes this gap to imbalances between shared and language-specific neurons in multilingual representations. We propose Cross-Lingual Activation Steering (CLAS), a training-free inference-time intervention that selectively modulates neuron activations. We evaluate CLAS on classification and generation benchmarks, achieving average improvements of 2.3% (Acc.) and 3.4% (F1) respectively, while maintaining high-resource language performance. We discover that effective transfer operates through functional divergence rather than strict alignment; performance gains correlate with increased language cluster separation. Our results demonstrate that targeted activation steering can unlock latent multilingual capacity in existing models without modification to model weights.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2601.16390
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.16390 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2601.16390 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.16390 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.