conftrace_

reward-guided search

4 papers

Explore in graph

Also known as

RGS

Co-occurring keywords · papers mentioning both

language model alignment (2) outcome reward model (1) preference consistency (1) score consistency (1) angular margin (1) softmax margin (1) feature discrimination (1) neural network (1) sequential question answering (1) neural semantic parsing (1)

Papers

From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment ACL 2025 ARGS: Alignment as Reward-Guided Search ICLR 2024 Loss Function Search for Face Recognition ICML 2020 Search-based Neural Structured Learning for Sequential Question Answering ACL 2017