cs.AIOct 31, 2026

Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations

Authors: Stuart Farmer

Organizations: Casa Dilauro Independent Research House

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.

Figures & tables

Explore similar work

CardsList
  1. Inducing Sustained Creativity and Diversity in Large Language Models

    Mar 19, 2026Queenie Luo, Gary King, Michael Puett +1Language Model DecodingDiverse Text Generation

  2. Recipes for Creativity: Iterative Generation and Evaluation in Large Language Models

    Aug 7, 2026Rens Anderson, Tessa Verhoef, Amirhossein ZohrehvandCreativity AssessmentLLM Evaluation

  3. Training Reasoning Models to Generate Diverse Scientific Ideas

    Oct 15, 2026Manya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi +3Diverse Text GenerationScientific Hypothesis Generation