Post-hoc model-based compression of reasoning traces cuts training tokens to 12-30% and speeds training 2-7.6x while retaining up to 96% of raw-trace accuracy, though raw traces remain superior at every scale.
Distilling Reasoning Capabilities into Smaller Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
citing papers explorer
-
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation
Post-hoc model-based compression of reasoning traces cuts training tokens to 12-30% and speeds training 2-7.6x while retaining up to 96% of raw-trace accuracy, though raw traces remain superior at every scale.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.