Safety
Cross-Lingual Activation Steering for Multilingual Language Models
arXiv:2601.16390v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant lan
arXiv:2601.16390v2 Announce Type: replace-cross Abstract: 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.
Related
- Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance
- Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs
- LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish
Source: arXiv cs.AI | 2026-10-07