无锚点多样化并行LLM创意生成
Anchorless Diversification for Parallel LLM Ideation
AI总结:
研究无锚点方法(如语义方向分层)在并行LLM创意生成中实现候选池多样化,无需依赖种子想法,在多样性、质量和计算效率上优于有锚点基线。
摘要:
大型语言模型越来越多地用于生成创意任务的候选想法池,其中广泛探索是有价值的。在此场景下,并行推理在拓宽池的同时保持质量和成本效率时具有吸引力。我们研究推理时控制以实现候选池多样化,探究无锚点方法是否能与依赖观察到的种子想法的方法相抗衡。在三个创意任务族中,我们在中性和群体参照发散指令下,比较了独立生成和语义方向分层与自我、同伴和代表性锚点基线。群体参照发散是一个强大的低成本基线,在保持质量代理的同时增加了语义多样性。语义方向分层更强:一次规划调用即可组织跨广泛语义方向的生成,产生最佳的多样性-质量-计算前沿。锚点再生在最终池多样性上可能很强,但其优势在完整流水线令牌核算下缩小。这些结果为开放式LLM创意生建立实用的无锚点基线。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。