基於評估的迭代式計畫提取，用於長篇敘事文本生成

摘要

計畫與寫作是長篇敘事文本生成中常見的階層式方法，首先創建一個計畫來指導敘事寫作。根據這種方法，一些研究依賴於簡單地提示大型語言模型進行規劃，這通常會產生次優結果。在本文中，我們提出了一個名為評估引導的迭代計畫提取框架，用於長篇敘事文本生成（EIPE-text），該框架從敘事語料庫中提取計畫，並利用提取的計畫來構建更好的規劃器。EIPE-text 包括三個階段：計畫提取、學習和推理。在計畫提取階段，它從敘事語料庫中迭代地提取和改進計畫，並構建計畫語料庫。我們提出了一個基於問答（QA）的評估機制，自動評估計畫並生成詳細的計畫改進指示，以指導迭代改進。在學習階段，我們通過與計畫語料庫進行微調或在計畫語料庫中使用示例進行上下文學習，建立一個更好的規劃器。最後，我們利用階層式方法生成長篇敘事。我們在小說和故事敘述領域評估了 EIPE-text 的有效性。基於 GPT-4 的評估和人類評估都表明，我們的方法能夠生成更具連貫性和相關性的長篇敘事。我們的程式碼將在未來發布。

English

Plan-and-Write is a common hierarchical approach in long-form narrative text generation, which first creates a plan to guide the narrative writing. Following this approach, several studies rely on simply prompting large language models for planning, which often yields suboptimal results. In this paper, we propose a new framework called Evaluation-guided Iterative Plan Extraction for long-form narrative text generation (EIPE-text), which extracts plans from the corpus of narratives and utilizes the extracted plans to construct a better planner. EIPE-text has three stages: plan extraction, learning, and inference. In the plan extraction stage, it iteratively extracts and improves plans from the narrative corpus and constructs a plan corpus. We propose a question answer (QA) based evaluation mechanism to automatically evaluate the plans and generate detailed plan refinement instructions to guide the iterative improvement. In the learning stage, we build a better planner by fine-tuning with the plan corpus or in-context learning with examples in the plan corpus. Finally, we leverage a hierarchical approach to generate long-form narratives. We evaluate the effectiveness of EIPE-text in the domains of novels and storytelling. Both GPT-4-based evaluations and human evaluations demonstrate that our method can generate more coherent and relevant long-form narratives. Our code will be released in the future.

基於評估的迭代式計畫提取，用於長篇敘事文本生成

EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation

摘要

Support