arXiv (All)
open access
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),
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Latent Mechanisms of Language Control in Multilingual Language Models#809784
- Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall#1117895
- Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation#792738
- Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation#788738
- Improving ASA-PS classification accuracy using private-deployment-compatible large language models: a multilingual evaluation#456878
Record · ID 819780
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive