Task-reward reinforcement learning yields robust gains on math benchmarks for models like Llama-3.2-3B while distribution sharpening alone delivers only limited and unstable improvements.
Breaking the beam search curse: A study of (re-)scoring methods and stopping criteria for neural machine translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Distribution Sharpening: The Importance of Task Rewards
Task-reward reinforcement learning yields robust gains on math benchmarks for models like Llama-3.2-3B while distribution sharpening alone delivers only limited and unstable improvements.