@inproceedings{li-etal-2026-unlocking,
    title = "Unlocking Multilingual Reasoning Capability of {LLM}s and {LVLM}s through Representation Engineering",
    author = "Li, Qiming  and
      Feng, Xiaocheng  and
      Ma, Yixuan  and
      Chen, Ruihan  and
      Tong, Zihe  and
      Ye, Zekai  and
      Feng, Xiachong  and
      Qin, Libo  and
      Ren, Haoyu  and
      Chen, Kun  and
      Lu, Yunfei  and
      Tu, Dandan  and
      Qin, Bing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1138/",
    pages = "24810--24829",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input{--}output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48{\%} and up to 7.54{\%} in low-resource languages (e.g., Thai and Swahili), while improving input-output language consistency by 3.78{\%}."
}