用强化学习优化提示，让大模型既快又懂、还能解释清楚。
Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text
- 分三步：先学自然语言规则，再蒸馏小模型，最后强化学习扩展推理。
- 在多个数据集上性能超越现有方法，解释质量也更优。
- 适合需要透明推理和高效部署的复杂文本任务场景。
大语言模型在文本分类上表现优异，但现有方法存在权衡：监督微调可扩展但缺乏对复杂文本的推理能力且透明度低；离散提示优化虽能生成人类可读指令，却难以兼顾性能与可扩展性。我们提出eXTC（可解释文本分类器），包含三个渐进阶段：(1) 通过新型结构化提示优化算法，从自然语言中学习标准操作流程（SOP，即规则手册）；(2) 基于SOP对大型教师模型进行推理蒸馏，生成紧凑的小型语言模型；(3) 通过强化学习扩展初始SOP之外的推理能力。该设计使eXTC具备（i）通过紧凑模型实现快速推理，（ii）推理时提供局部解释路径，以及（iii）全局模块化的领域规则解释，并在多个基准测试中显著优于现有范式，且各阶段均带来性能提升。
原文摘要 · Abstract (English)
LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability. We introduce eXTC (eXplainable Text Classifier) with three progressive stages: (1) learning a Standard Operating Procedure (SOP, or rulebook) in natural language via a new Structured Prompt Optimization algorithm; (2) SOP-grounded reasoning distillation from a large teacher LLM into a compact LM; and (3) expanding reasoning capabilities beyond the initial SOP via reinforcement learning. This design enables eXTC to provide (i) fast inference via a compact LM, with (ii) inference-time local reasoning traces, alongside a global, modular explanation of its learned domain rules, while (iii) significantly outperforming existing paradigms across diverse benchmarks in both classification performance and explanation quality, with stage-by-stage gains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。