Year: 2025
Type: conference-paper
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 RECUR-RENT 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.
Authors: Yuxiang Liu, Kevin Chen-Chuan Chang
Institution: University of Illinois Urbana-Champaign
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G3668672548, BIGDATA: F: Bringing Interactive Data Management to Scientists, Analysts, and the Masses: A Holistic Unification of Spreadsheets and Databases, III: Small: Social Discovery of Users and Content in Social Media Through Similarity-Based and Graph-Based Inference of Attributes and Queries
OpenAlex ID: W4412889979