ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penalizing sycophancy.
Rethinking supervised fine-tuning: Em- phasizing key answer tokens for improved llm accuracy
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AlphaToken decouples adaptation and stability into path-aware token valuations for LLM post-training using a Fisher-drift proxy to mask low-value tokens and improve performance while reducing catastrophic forgetting.
citing papers explorer
-
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penalizing sycophancy.
-
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
AlphaToken decouples adaptation and stability into path-aware token valuations for LLM post-training using a Fisher-drift proxy to mask low-value tokens and improve performance while reducing catastrophic forgetting.