Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.
Qa-lign: Aligning llms through constitutionally decomposed qa.arXiv preprint arXiv:2506.08123
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
RaR uses aggregated rubric feedback as rewards in on-policy RL, delivering up to 31% relative gains on HealthBench and 7% on GPQA-Diamond versus direct Likert LLM-as-judge baselines.
RECAP is an inference-time framework using cognitive appraisal theory to enhance emotional alignment and transparency in medical dialogue systems across model scales.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.
-
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
RaR uses aggregated rubric feedback as rewards in on-policy RL, delivering up to 31% relative gains on HealthBench and 7% on GPQA-Diamond versus direct Likert LLM-as-judge baselines.
-
RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
RECAP is an inference-time framework using cognitive appraisal theory to enhance emotional alignment and transparency in medical dialogue systems across model scales.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.