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.
Mitigating Metric Bias in Minimum B ayes Risk Decoding
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
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.