SOURCE-LINKED INTELLIGENCE
Latent Mechanisms of Language Control in Multilingual Language Models
Multilingual large language models can exhibit unintended code-switching -- unnecessarily alternating between languages during generation. We present a comparative study of three methods that identify language-controlling latents in cross-layer transcoders: activation value-based selection (ValSel), activation frequency-based selection (FreqSel), and LLM-generated latent annotation-based selection (AnnSel). To evaluate the efficacy of these methods in identifying language-controlling latents, we introduce two multilingual benchmarks that exhibit code-switching for fine-grained analysis of lang
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-08-31T20:21:21.000Z
First collected: 2026-09-21T06:21:59.299Z. This is not the publication date.