Introspective Training annotates data with natural-language feedback from a thinking reward model and conditions all LLM training stages on that feedback, bending scaling curves for up to 2.8x compute efficiency gains and superior math/code performance.
{explanation}\n\n{document}
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
Introspective Training annotates data with natural-language feedback from a thinking reward model and conditions all LLM training stages on that feedback, bending scaling curves for up to 2.8x compute efficiency gains and superior math/code performance.