让大模型生成更美观的文本，提升可读性与一致性
Textual Aesthetics in Large Language Models
- 提出TAPO方法，用美学优化微调模型而不牺牲内容正确性
- 构建了名为TexAes的文本美学数据集，支持评估与训练
- 在AlpacalEval和Anera-hard上同时提升美观度与通用性能
图像美学在图像生成领域至关重要，但文本美学尚未得到充分研究。随着大语言模型（LLM）广泛应用，以往工作主要关注内容正确性和回复帮助性，而忽视了文本美学的重要性。本文提出一种美学润色流程，并构建名为TexAes的文本美学数据集。我们设计基于直接偏好优化的文本美学微调方法TAPO，能在不损害内容正确性的前提下提升文本美感。此外，开发了两种评估方法：一种基于文本分析，另一种结合图像分析。实验表明，使用该数据集并采用TAPO方法，不仅能显著提升文本美学评分，还能在AlpacalEval和Anera-hard等通用评测集上获得更好表现。
原文摘要 · Abstract (English)
Image aesthetics is a crucial metric in the field of image generation. However, textual aesthetics has not been sufficiently explored. With the widespread application of large language models (LLMs), previous work has primarily focused on the correctness of content and the helpfulness of responses. Nonetheless, providing responses with textual aesthetics is also an important factor for LLMs, which can offer a cleaner layout and ensure greater consistency and coherence in content. In this work, we introduce a pipeline for aesthetics polishing and help construct a textual aesthetics dataset named TexAes. We propose a textual aesthetics-powered fine-tuning method based on direct preference optimization, termed TAPO, which leverages textual aesthetics without compromising content correctness. Additionally, we develop two evaluation methods for textual aesthetics based on text and image analysis, respectively. Our experiments demonstrate that using textual aesthetics data and employing the TAPO fine-tuning method not only improves aesthetic scores but also enhances performance on general evaluation datasets such as AlpacalEval and Anera-hard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。