Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages

arXiv:2611.03317 · cs.CL · Submitted 2026-11-02 · Read on arXiv

cs.CL

Submitted: 2026-11-02

Updated: 2026-11-02

Comments: 30 pages, 12 figures, 11 tables

Code: https://github.com/lucindalaurent/SteeringWithMultilingualLexicon

License: http://creativecommons.org/licenses/by/4.0/

The gist: Activation steering offers a lightweight mechanism for controlling model behavior, but existing methods depend on sentence-level contrastive data that is unavailable for most of the world's languages.

Terminology

Abstract

Activation steering offers a lightweight mechanism for controlling model behavior, but existing methods depend on sentence-level contrastive data that is unavailable for most of the world's languages. We show that multilingual sentiment lexicons are a viable substitute across three model families: aggregated multilingual lexicons outperform English-derived steering vectors for mid- and low-resource languages, while monolingual lexicons remain stronger for languages a model has specialized in during pre-training. The steering efficacy is mechanistically dictated by both representational density and pre-training priors. Large-magnitude English vectors overwhelm the compact representations of low-resource languages, causing "linguistic collapse." This fragility is mitigated by the norm-dampening of multilingual aggregation. Architectural biases, including bilingual specialization penalty and latent numerical rigidity, also heavily constrain cross-lingual steering responsiveness. Ultimately, our work establishes lexicons as a practical steering signal and offers a comprehensive mechanistic account of cross-lingual steering dynamics.

Sources

Related papers