用随机概念注入提示词，提升大模型输出多样性。
Addressing LLM Diversity by Infusing Random Concepts
- 在提示词前添加无关随机词，激发模型生成更多样内容。
- 实验显示多种大模型输出多样性显著提升。
- 适合关注生成多样性与评估方法的研究者。
大型语言模型（LLMs）常产生多样性不足的输出。本文研究在提示词中注入随机概念是否能提升生成内容的多样性。为此，我们设计了一套系统性评估协议：以‘列举10位好莱坞演员’类问题为测试基准，分析模型输出的多样性指标。在多个主流大模型上的实验表明，在提示词前添加与任务无关的随机词或句子，可显著提升输出多样性。该结果及评估协议为未来研究开辟新方向，例如如何将随机性注入应用于其他领域，并推动对大模型多样性进行更系统的基准评测。
原文摘要 · Abstract (English)
Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity of the generated outputs. To benchmark the approach, we design a systematic evaluation protocol which involves prompting an LLM with questions of the form "Name 10 Hollywood actors", and analyzing diversity measures of the resulting LLM outputs. Our experiments on multiple LLMs show that prepending random words/sentences unrelated to the prompt result in greater diversity in the outputs of LLMs. We believe that this promising result and the evaluation protocol opens up interesting avenues for future work, such as how infusing randomness into LLMs could be applied to other domains. Further, the evaluation protocol could also inspire research into benchmarking LLM diversity more systematically.
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。