conftrace_

intrinsic self-correction

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) convergence behavior (1) self-verification (1) confidence-aware decoding (1) reasoning correction (1) moral reasoning (1) ai safety (1) convergence analysis (1) curriculum learning (1)

Papers

On the Convergence of Moral Self-Correction in Large Language Models IJCNLP 2025 ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification ICML 2025