English

Writing Like the Best: Exemplar-Based Expository Text Generation

Computation and Language 2025-05-27 v1 Artificial Intelligence

Abstract

We introduce the Exemplar-Based Expository Text Generation task, aiming to generate an expository text on a new topic using an exemplar on a similar topic. Current methods fall short due to their reliance on extensive exemplar data, difficulty in adapting topic-specific content, and issues with long-text coherence. To address these challenges, we propose the concept of Adaptive Imitation and present a novel Recurrent Plan-then-Adapt (RePA) framework. RePA leverages large language models (LLMs) for effective adaptive imitation through a fine-grained plan-then-adapt process. RePA also enables recurrent segment-by-segment imitation, supported by two memory structures that enhance input clarity and output coherence. We also develop task-specific evaluation metrics--imitativeness, adaptiveness, and adaptive-imitativeness--using LLMs as evaluators. Experimental results across our collected three diverse datasets demonstrate that RePA surpasses existing baselines in producing factual, consistent, and relevant texts for this task.

Keywords

Cite

@article{arxiv.2505.18859,
  title  = {Writing Like the Best: Exemplar-Based Expository Text Generation},
  author = {Yuxiang Liu and Kevin Chen-Chuan Chang},
  journal= {arXiv preprint arXiv:2505.18859},
  year   = {2025}
}

Comments

Accepted to ACL 2025. Camera-ready version

R2 v1 2026-07-01T02:36:25.758Z