九歌-推敲：一款面向古典诗词润色的可解释人机协作系统
Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement
浏览论文内容
中文总结 AI 辅助
针对现有AI诗词系统削弱用户创作能动性的问题，提出人机协作系统Jiuge-Tuiqiao，通过三元模型实现可控可解释的诗词润色，提升了创作相关性能。
中文摘要 AI 辅助
古典诗词创作长期重视“推敲”，即对字词、意象和韵律的迭代润色。然而，当前许多AI诗词系统采用一次性生成范式，将用户降格为提示提供者，削弱了用户的创作能动性。我们提出Jiuge-Tuiqiao（九歌-推敲），一款面向古典诗词创作的交互式人机协作系统。该系统基于三元模型设计：用户驱动控制、古籍引导证据、AI辅助生成。用户可锁定字符或诗句，获取实时韵律反馈，以及基于高频搭配、困惑度（PPL）排序的古典诗句、从古典百科全书提取的结构化知识生成的可解释润色建议。该设计将AI从自主生成器转变为支持用户自身诗词润色过程的后台助手。初步实验和用户反馈表明，Jiuge-Tuiqiao提升了古典诗词创作的可控性、可解释性和用户参与度。
英文摘要
Classical Chinese poetry composition has long valued Tuiqiao, the iterative refinement of words, imagery, and prosody. However, many current AI poetry systems follow a one-shot generation paradigm, which reduces users to prompt providers and weakens their creative agency. We present Jiuge-Tuiqiao, an interactive human-AI collaborative system for classical Chinese poetry composition. The system is designed around a triadic model: user-driven control, ancient-guided evidence, and AI-assisted generation. Users can lock characters or lines, receive real-time prosody feedback, and obtain interpretable refinement suggestions grounded in high-frequency collocations, PPL-ranked classical lines, and structured knowledge extracted from classical encyclopedias. This design turns AI from an autonomous generator into a background assistant that supports the user's own process of poetic refinement. Preliminary experiments and user feedback suggest that Jiuge-Tuiqiao improves controllability, interpretability, and user engagement in classical poetry composition.
发表机构
- Tsinghua University（清华大学）
- Beijing National Research Center For Information Science And Technology（北京信息科学与技术国家研究中心）
- Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能国际研究院）
- Rixin College, Tsinghua University（清华大学日新书院）
- Department of Statistics and Data Science, Tsinghua University（清华大学统计与数据科学系）
- Jiangsu Normal University（江苏师范大学）
机构由 AI 辅助整理，请以论文原文为准。
