conftrace_

sequence-level optimization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

policy gradient (2) hybrid supervision (1) token-level policy (1) preference model (1) large language model (1) longest common subsequence (1) sequence-level scoring (1) reward model training (1) alignment framework (1) token-level prediction (1)

Papers

HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025 Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion EMNLP 2024 CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization EMNLP 2018