Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Paper • 2609.32444 • Published • 23
Ben Calvert
bencalvert04
·
AI & ML interests
Building evals for agents
Recent Activity
upvoted a paper about 1 month ago
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It upvoted a paper about 2 months ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation new activity 4 months ago
harborframework/parity-experiments:Add parity experiments for programbenchOrganizations
None yet
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
Add parity experiments for programbench
#262 opened 4 months ago
by bencalvert04
liked a
dataset 4 months ago