不依赖种子想法，用新方法让大模型并行生成更多创意点子。
Anchorless Diversification for Parallel LLM Ideation
- 提出无锚定的并行生成策略，无需依赖初始想法。
- 单次规划调用可实现最佳多样性与质量平衡，提升创意覆盖范围。
- 适合需要快速生成多样创意的场景，如产品设计、内容策划。
大语言模型越来越多地用于创造性任务中生成候选想法池，此时广泛探索尤为关键。并行推理在此场景中具有吸引力，可在保持质量与成本效率的前提下扩大想法池。我们研究了推理时的控制策略以提升候选池的多样性，探讨无锚定方法是否能媲美依赖已有种子想法的方法。在三种创造性任务类型中，比较了独立生成与语义方向分层策略，以及自锚、同伴锚和代表锚基线方法，在中性指令与群体参照型发散指令下表现。群体参照型发散是一种低成本强基线，能显著提升语义多样性且维持质量指标。语义方向分层策略更优：仅需一次规划调用即可组织跨广泛语义方向的生成，达到最优多样性-质量-计算权衡。锚定重生成在最终池多样性上表现良好，但在全管道词元开销核算下优势减弱。本研究确立了开放式大模型创意生成的实用无锚定基准。
原文摘要 · Abstract (English)
LLMs are increasingly used to generate candidate-idea pools for creative tasks where broad exploration is valuable. Parallel inference can be attractive in this setting when it broadens the pool while retaining quality and cost efficiency. We study inference-time controls for candidate-pool diversification, asking whether anchorless methods can rival methods that depend on observed seed ideas. Across three creative task families, we compare independent generation and semantic direction stratification with self-, peer-, and representative-anchor baselines, under neutral and population-referential divergent instructions. Population-referential divergence is a strong low-cost baseline, increasing semantic diversity while preserving quality proxies. Semantic direction stratification is stronger: a single planning call organizes generations across broad semantic directions, yielding the best diversity--quality--compute frontier. Anchored regeneration can be strong in final-pool diversity, but its advantage shrinks under full-pipeline token accounting. These results establish practical anchorless baselines for open-ended LLM ideation.
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。