conftrace_

preference calibration

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

ethical framework (1) large language model (1) model personalization (1) moral reasoning (1) positive-unlabeled learning (1) residual stream (1) binary feedback (1) preference optimization (1)

Papers

Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework ACL 2026 Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models ACL 2026