EMNLP Findings2025
Over-Generation and Compaction: A Prompting Strategy for Procedural Text Adaptation with Large Language Models
HyeongSik Kim, Xu Yanheng, Chaoqun Dong, Fei Du
Abstract
Procedural text adaptation-such as modifying recipes or revising instructional guides-has traditionally relied on specialized models extensively fine-tuned for specific domains. To address the scalability limitations of such approaches, recent research has increasingly turned to general-purpose large language models (LLMs). However, existing prompting strategies for LLMs often yield superficial or erroneous adaptations due to alignment-induced biases and the inherent complexity of procedural editing. To overcome these challenges, we propose the Over-generation-and-Compaction (OC) prompting strategy, which first elicits diverse procedural details to leverage the model's latent knowledge, and subsequently compacts them into concise, coherent adaptations. We further introduce Recipe Consistency & Feasibility (RCF), a novel metric for systematically evaluating the procedural validity and practical feasibility of recipe adaptations. Experiments on public datasets show that OC substantially enhances adaptation consistency and feasibility over baseline prompting methods, without requiring additional fine-tuning or curated training resources.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on2
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
Related papers
- Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt LearningQizhou Chen, Taolin Zhang, Xiaofeng He, Dongyang Li et al.EMNLP 2024 · 1 citation
- Exploring the Transferability of Visual Prompting for Multimodal Large Language ModelsYichi Zhang, Yinpeng Dong, Siyuan Zhang, Tianzan Min et al.CVPR 2024 · 10 citations
- No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt OptimizationWenhang Shi, Yiren Chen, Shuqing Bian, Xinyi Zhang et al.NeurIPS 2025 · 9 citations
- Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language ModelsZijun Wu, Yongkang Wu, Lili MouICLR 2024 · 9 citations
- Gradient-Guided Multi-Judge Prompt OptimizationChenzhuo Zhao, Xinda Wang, Pu Zhao, Yue Huang et al.ACL 2026
