Interpretability probes on latent reasoning vectors enable training-free interventions that raise LLM reasoning accuracy across scales and tasks.
Proceedings of the AAAI Conference on Artificial Intelligence , author=
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
-
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
Interpretability probes on latent reasoning vectors enable training-free interventions that raise LLM reasoning accuracy across scales and tasks.