通过语义筛选提升多语言谜题生成的创意与文化契合度
Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation
- 用语义拒绝机制强制输出新颖且符合文化的创意内容
- 在阿拉伯语中RiddleScore提升57.1%，日语Distinct-2达0.915
- 无需微调即可实现高质量多语言创造性生成，适合文化相关任务
语言模型在多语言创造力测试中面临挑战，需生成具有文化根基的抽象内容。传统提示方法常导致重复或浅层输出。本文提出自适应原创性过滤（AOF），通过语义拒绝机制强化新颖性与文化真实性。为评估质量，提出RiddleScore，融合新颖性、多样性、流畅性与答案匹配度。AOF在日语中使Distinct-2达0.915，降低Self-BLEU至0.177，阿拉伯语中RiddleScore最高提升57.1%。人工评估证实流畅性、创意与文化契合度显著提升。虽不同语言表现差异明显（阿拉伯语在RiddleScore上增益大于Distinct-2，日语变化相近），但该方法可拓展至更广泛的创造性任务。整体而言，无需微调的语义过滤结合综合评估，为生成富含文化内涵的内容提供轻量路径。
原文摘要 · Abstract (English)
Language models are increasingly tested on multilingual creativity, demanding culturally grounded, abstract generations. Standard prompting methods often produce repetitive or shallow outputs. We introduce Adaptive Originality Filtering (AOF), a prompting strategy that enforces novelty and cultural fidelity via semantic rejection. To assess quality, we propose RiddleScore, a metric combining novelty, diversity, fluency, and answer alignment. AOF improves Distinct-2 (0.915 in Japanese), reduces Self-BLEU (0.177), and raises RiddleScore (up to +57.1% in Arabic). Human evaluations confirm fluency, creativity, and cultural fit gains. However, improvements vary: Arabic shows greater RiddleScore gains than Distinct-2; Japanese sees similar changes. Though focused on riddles, our method may apply to broader creative tasks. Overall, semantic filtering with composite evaluation offers a lightweight path to culturally rich generation without fine-tuning.
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。