eXTC learns a natural-language SOP via structured prompt optimization, distills it into a compact LM, and extends it with RL to deliver fast inference plus global rules and local traces while claiming benchmark gains over prior paradigms.
InFindings of the association for computa- tional linguistics: EMNLP 2020, pages 2898–2904
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text
eXTC learns a natural-language SOP via structured prompt optimization, distills it into a compact LM, and extends it with RL to deliver fast inference plus global rules and local traces while claiming benchmark gains over prior paradigms.