Confident Decoding selects reliable intermediate layers via entropy-guided backward search to bypass final-layer alignment perturbations in LLMs, improving reasoning performance.
Layer-order inversion: Rethinking latent multi-hop reasoning in large language models.arXiv preprint arXiv:2601.03542,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Confident Decoding selects reliable intermediate layers via entropy-guided backward search to bypass final-layer alignment perturbations in LLMs, improving reasoning performance.
- Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models