概念引导提示法提升 LLM 生成食谱的多样性
Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations
arXiv 上的新论文，一个提示词小改动就能把生成内容的多样性从 13% 拉到 47%，做创意生成或探索类任务的可以试试这套思路。
一篇 arXiv 论文提出概念引导提示方法，让 LLM 先生成主题概念再在每个概念内作答。在生成 1,000 份食谱的任务中，该方法语义覆盖率达到 47.0%，优于先题策略的 35.1% 和随机策略的 13.1%，并与人类撰写的语料库做了对比。论文同时指出结果仅限食谱任务，方案质量和泛化性有待验证。
Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations
Novelty in solution generation supports automated discovery, but LLM outputs can remain repetitive. To address this, we propose a simple concept-guided prompting method that generates thematic concepts before responses within each of these concepts. To demonstrate, we generated 1,000 recipes for a recipe book task and compared the results against a human-authored corpus. Two naive prompting strategies were compared as baselines. Concept-guided prompting outperformed both baselines in all cases and reached semantic coverage of 47.0% versus 35.1% and 13.1% in respective prior-title and nonce prompt strategies. These findings suggest broader population exploration and diversity, but remain contained to this specific task. Further work is needed to determine the quality of solutions and generalizability.
