Skip to content
conftrace_

neuron collapse

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reward hacking (2) outcome reward model (1) test-time scaling (1) knowledge retention (1) deductive reasoning (1) model alignment (1) language model alignment (1) preference optimization (1) kl divergence (1) direct preference optimization (1)

Papers

Logical Reasoning with Outcome Reward Models for Test-Time Scaling EMNLP 2025 Weights-Rotated Preference Optimization for Large Language Models EMNLP 2025