Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
DecisionRank: On-Policy Distillation for Decision-Model Rerankers
Yanran Wu, Dian Yu, Chongyang Bai +10
Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowled…
cs.CL2025
Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
Bolian Li, Yanran Wu, Xinyu Luo +1
Aligning large language models (LLMs) with human preferences has become a critical step in their development. Recent research has increasingly focused on test-time alignment, where…