Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged as a more efficient and interpretable technique for adapting models to a target language. Yet, no dedicated benchmarks or evaluation protocols exist to quantify the effectiveness of steering techniques. We introduce CLaS-Bench, a lightweight parallel-question benchmark for evaluating language-forcing behavior in LLMs across 32 languages, enabling systematic evaluation of multilingual steering methods. We evaluate a broad array of steering techniques, including residual-stream DiffMean interventions, probe-derived directions, language-specific neurons, PCA/LDA vectors, Sparse Autoencoders, and prompting baselines. Steering performance is measured along two axes: language control and semantic relevance, combined into a single harmonic-mean steering score. We find that across languages simple residual-based DiffMean method consistently outperforms all other methods. Moreover, a layer-wise analysis reveals that language-specific structure emerges predominantly in later layers and steering directions cluster based on language family. CLaS-Bench is the first standardized benchmark for multilingual steering, enabling both rigorous scientific analysis of language representations and practical evaluation of steering as a low-cost adaptation alternative.

翻译：理解和控制大语言模型（LLM）的行为是多语言自然语言处理中日益重要的课题。除了提示或微调之外，导向技术——即在推理过程中操纵内部表征——已成为一种更高效、更可解释的模型适应目标语言的方法。然而，目前尚缺乏专门的基准测试或评估协议来量化导向技术的有效性。本文介绍了CLaS-Bench，一个轻量级的平行问题基准测试，用于评估LLM在32种语言中的语言强制行为，从而实现对多语言导向方法的系统评估。我们评估了广泛的导向技术，包括残差流DiffMean干预、探针导出的方向、语言特定神经元、PCA/LDA向量、稀疏自编码器以及提示基线。导向性能从两个维度进行衡量：语言控制与语义相关性，二者结合为一个单一的调和平均导向分数。我们发现，在所有语言中，基于残差的简单DiffMean方法始终优于其他所有方法。此外，分层分析表明，语言特定结构主要出现在较深层，且导向方向根据语系形成聚类。CLaS-Bench是首个用于多语言导向的标准化基准测试，既能支持对语言表征的严谨科学分析，也能作为低成本适应替代方案对导向技术进行实际评估。