arXiv cs.CL· Stuart Farmer·· 11 小时前AI 评分22
概念引导提示策略提升 LLM 生成食谱的多样性
Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations
AI 导读
研究者提出一种概念引导提示方法，让 LLM 在生成回答前先产出主题概念，再在每个概念内生成内容。在食谱书任务中生成 1000 份食谱并与人工语料对比，该方法语义覆盖率达 47.0%，高于 prior-title 策略的 35.1% 和 nonce 提示策略的 13.1%。结果表明其能拓展种群探索与多样性，但结论仅限该特定任务，方案质量与泛化性仍待验证。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2611.01171 [cs.AI] |
| (or arXiv:2611.01171v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01171 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Stuart Farmer [view email]
[v1]
Sat, 31 Oct 2026 18:15:04 UTC (629 KB)
来源：arXiv cs.CL · arxiv.org