不改模型，用双引导机制让大模型输出更丰富。
G2: Guided Generation for Enhanced Output Diversity in LLMs
- 用两个引导模块在解码时干预生成过程
- 在保持输出质量前提下，显著提升多样性
- 适合需要多变结果的创作与推理任务
大型语言模型在自然语言处理任务中表现卓越，但其输出多样性不足，多次生成内容高度相似，严重影响创意写作和推理等需多样化输出的任务。现有方法如温度调节虽能提升多样性，却牺牲输出质量。本文提出无需训练、可即插即用的G2方法，通过基础生成器与双引导模块，在解码阶段进行干预，使生成结果在保持原查询条件下的多样性得到增强。大量实验表明，G2有效提升了输出多样性，同时维持了多样性和质量之间的最优平衡。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in output diversity, often generating highly similar content across multiple attempts. This limitation significantly affects tasks requiring diverse outputs, from creative writing to reasoning. Existing solutions, like temperature scaling, enhance diversity by modifying probability distributions but compromise output quality. We propose Guide-to-Generation (G2), a training-free plug-and-play method that enhances output diversity while preserving generation quality. G2 employs a base generator alongside dual Guides, which guide the generation process through decoding-based interventions to encourage more diverse outputs conditioned on the original query. Comprehensive experiments demonstrate that G2 effectively improves output diversity while maintaining an optimal balance between diversity and quality.
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。