提升大模型输出多样性，让机器回答更像人类多样思考。
Growing a Tail: Increasing Output Diversity in Large Language Models
- 用温度采样、多视角提示和多模型聚合提升生成多样性。
- 组合方法使模型输出多样性显著提高，但仍低于人类水平。
- 适合关注AI公平性与文化多样性研究者阅读。
大型语言模型在需要多样化回答的任务中表现如何？我们评估了多个模型对多答案问题的响应多样性，发现其输出高度集中，远不如人类响应呈现长尾分布。通过三种简单实用方法——提高生成温度、单一提示引导多视角回答、整合多个模型输出——可显著提升多样性，尤其组合使用效果更佳。尽管如此，单模型输出仍普遍不及人类多样性。研究结果对需保护文化多样性的AI政策与治理具有启示意义。
原文摘要 · Abstract (English)
How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of several language models to questions with multiple possible answers, comparing them with human responses. Our findings suggest that models' responses are highly concentrated, reflecting narrow, mainstream outputs, in comparison to humans, whose responses exhibit a much longer-tail. We examine three simple and practical ways to increase output diversity: 1) increasing generation randomness via temperature sampling; 2) prompting models to answer from diverse perspectives using a single prompt; 3) aggregating outputs from several models. We find that these interventions, especially when combined, can substantially increase output diversity, although single-model outputs generally remain less diverse than the human baseline. We discuss potential implications of these findings for future work in AI policy and governance that wishes to preserve cultural diversity, an essential building block of a democratic social fabric.
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。