@inproceedings{zwirner-etal-2026-evaluating,
    title = "Evaluating the Impact of {SAE}-based Language Steering on {LLM} Performance",
    author = "Zwirner, Sebastian  and
      Hu, Wentao  and
      Aoki, Koshiro  and
      Kawahara, Daisuke",
    editor = "Baez Santamaria, Selene  and
      Somayajula, Sai Ashish  and
      Yamaguchi, Atsuki",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-srw.43/",
    pages = "555--568",
    ISBN = "979-8-89176-383-8",
    abstract = "Recent advances in Sparse Autoencoders (SAEs) have revealed interpretable features within large language models (LLMs), including features that are specific to individual languages.In prior work, these features have been used to steer a model{'}s output language.However, the impact of SAE-based language steering on output quality and task performance, as well as its relationship to simpler prompting-based approaches, remains unclear.In this work, we study the effects of language steering using SAE features across multiple tasks and models.We apply language-specific SAE feature steering to three LLMs from two model families and evaluate it on a translation task and a multilingual question-answering task.We compare SAE-based steering against prompting and language neuron-based steering, and examine a combined prompting-and-steering approach.On the translation task, SAE feature steering achieves an average target-language accuracy of 92{\%} across models and languages, consistently outperforming language neuron-based steering, but slightly underperforming prompting in language accuracy and output quality.In contrast, on the multilingual question-answering task, SAE-based steering enables stronger language control than prompting, and combining steering with prompting yields the best overall language control and task performance.These findings demonstrate the potential of SAE features as a tool for controllable multilingual generation."
}