VCM is a training-free decoding intervention that applies PMI-driven token elevation and variance-adaptive penalization to reduce repetitive degeneration in LLM open-ended generation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.
SemEval-2026 Task 7 presents a benchmark and two evaluation tracks for assessing LLMs on everyday knowledge in diverse languages and cultures without allowing training on the test data.
citing papers explorer
-
Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.