A monolingually trained linear probe on intermediate LLM representations predicts answer correctness zero-shot across typologically diverse languages, with confidence signals concentrated in middle layers.
InProceedings of the workshop on multimodal, multilingual natu- ral language generation and multilingual WebNLG Challenge (MM-NLG 2023), pages 1–9
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models
A monolingually trained linear probe on intermediate LLM representations predicts answer correctness zero-shot across typologically diverse languages, with confidence signals concentrated in middle layers.