Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text

2026-05-27 · Tianyang Zhou, Wenbo Chen, Pierre Jinghong Liang, Leman Akoglu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.29076

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning Text Classification

Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery

2022-03-08 · Niklas Funk, Svenja Menzenbach, Georgia Chalvatzaki, Jan Peters

Robot assembly discovery is a challenging problem that lives at the intersection of resource allocation and motion planning. The goal is to combine a predefined set of objects to form something new while considering task…

global-optimization Motion Planning Q-Learning Reinforcement Learning (RL)

Automatic Prompt Optimization for Dataset-Level Feature Discovery

2026-01-20 · Adrian Cosma, Oleg Szehr, David Kletz, Alessandro Antonucci 외 arxiv

Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discove…

UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection

2026-01-30 · Siran Peng, Weisong Zhao, Tianyu Fu, Chenxu Zhao 외 arxiv

Prompt agents have recently emerged as a promising paradigm for automated prompt optimization, framing prompt discovery as a sequential decision-making problem over a structured prompt space. While this formulation enabl…

GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning

2024-11-19 · Yuze Liu, Tingjie Liu, Tiehua Zhang, Youhua Xia 외

Large language models (LLMs) have demonstrated impressive success in a wide range of natural language processing (NLP) tasks due to their extensive general knowledge of the world. Recent works discovered that the perform…

General Knowledge Prompt Engineering Reinforcement Learning (RL)

Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning

2025-07-06 · Binbin Ji, Siddharth Agrawal, Qiance Tang, Yvonne Wu arxiv

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting st…

Reinforcement Learning Spatial Reasoning