教導語言模型微調 —— 一種受寫作教育啟發的方法

摘要

個性化文本生成是一個近年來引起廣泛關注的新興研究領域。這個方向上的大多數研究專注於通過設計定製特徵或模型來專注於特定領域。在這項工作中，我們提出了一種使用大型語言模型（LLMs）進行個性化文本生成的通用方法。受到寫作教育實踐的啟發，我們開發了一個多階段和多任務的框架，用於教導LLMs進行個性化生成。在寫作指導中，從來源進行寫作的任務通常被分解為涉及尋找、評估、摘要、綜合和整合信息的多個步驟。類似地，我們的個性化文本生成方法包括多個階段：檢索、排名、摘要、綜合和生成。此外，我們引入了一個多任務設置，有助於模型進一步提高其生成能力，這受到教育領域觀察到的一個現象的啟發，即學生的閱讀能力和寫作能力通常是相關的。我們在三個公開數據集上評估了我們的方法，每個數據集涵蓋不同且具代表性的領域。我們的結果顯示相對於各種基準線，顯著改善。

English

Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summarizing, synthesizing, and integrating information. Analogously, our approach to personalized text generation consists of multiple stages: retrieval, ranking, summarization, synthesis, and generation. In addition, we introduce a multitask setting that helps the model improve its generation ability further, which is inspired by the observation in education that a student's reading proficiency and writing ability are often correlated. We evaluate our approach on three public datasets, each of which covers a different and representative domain. Our results show significant improvements over a variety of baselines.

教導語言模型微調 —— 一種受寫作教育啟發的方法

Teach LLMs to Personalize -- An Approach inspired by Writing Education

摘要

Support