揭秘大模型生成文本时参数如何影响结果，给出实用调参指南。
Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
- 系统测试多种解码方法与参数组合，覆盖不同模型和文本类型。
- 发现最优参数因模型和任务而异，需针对性调整。
- 适合研究者和开发者优化生成质量，提升输出可靠性。
生成式大语言模型的解码策略是文本生成中的关键但常被忽视的环节。通过特定超参数引导，这些策略将模型产生的原始概率分布转化为连贯流畅的文本。本研究对多种解码方法、开源大模型、文本领域及评估协议进行了大规模实证分析，涵盖事实类（如新闻）与创意类（如小说）文本，并结合自动评估指标与人工判断。通过广泛的敏感性分析，我们提炼出超参数选择与调优的实际建议，指出最优配置随模型与任务而变化。综合这些发现，本研究为优化解码策略提供了可操作的指导，助力研究人员与实践者实现更高质量、更可靠、更适配上下文的文本生成效果。
原文摘要 · Abstract (English)
Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions produced by language models into coherent, fluent text. In this study, we undertake a large-scale empirical assessment of a range of decoding methods, open-source LLMs, textual domains, and evaluation protocols to determine how hyperparameter choices shape the outputs. Our experiments include both factual (e.g., news) and creative (e.g., fiction) domains, and incorporate a broad suite of automatic evaluation metrics alongside human judgments. Through extensive sensitivity analyses, we distill practical recommendations for selecting and tuning hyperparameters, noting that optimal configurations vary across models and tasks. By synthesizing these insights, this study provides actionable guidance for refining decoding strategies, enabling researchers and practitioners to achieve higher-quality, more reliable, and context-appropriate text generation outcomes.
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。