A three-stage SAE-plus-SVD steering recipe claims to make Hindi or Spanish the default language of an LLM at inference time, but the visible manuscript reports only expected, not measured, outcomes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
A three-stage SAE-plus-SVD steering recipe claims to make Hindi or Spanish the default language of an LLM at inference time, but the visible manuscript reports only expected, not measured, outcomes.