提出自适应解码方法GUARD，平衡长文本生成的连贯性与多样性。
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
- 融合全局熵与局部熵差，动态感知生成过程中的不确定性。
- 相比基线模型，生成速度提升显著，多样性与连贯性更优。
- 无需调参，适合追求高效高质量生成的应用场景。
开放域文本生成面临连贯性与多样性难以兼顾的挑战。尽管基于对比搜索的解码策略被提出以缓解此权衡，但其实际应用常受限于超参数敏感性和高计算开销。本文提出GUARD，一种自适应解码方法，通过创新的“全局-局部”不确定性驱动框架实现两者平衡。该方法结合全局熵估计与局部熵偏差，整合长期与短期不确定性信号。我们证明所提出的全局熵形式能有效抑制不确定性突变（如突然自信或熵激增），并提供无偏性和一致性理论保证。为降低计算负担，引入基于词元计数的简单有效惩罚项。实验表明，GUARD在保持文本多样性和连贯性的同时，显著提升生成速度。跨多维度的质量评估中，人工及大模型评价者均验证其卓越表现。代码已开源：https://github.com/YecanLee/GUARD。
原文摘要 · Abstract (English)
Open-ended text generation faces a critical challenge: balancing coherence with diversity in LLM outputs. While contrastive search-based decoding strategies have emerged to address this trade-off, their practical utility is often limited by hyperparameter dependence and high computational costs. We introduce GUARD, a self-adaptive decoding method that effectively balances these competing objectives through a novel "Glocal" uncertainty-driven framework. GUARD combines global entropy estimates with local entropy deviations to integrate both long-term and short-term uncertainty signals. We demonstrate that our proposed global entropy formulation effectively mitigates abrupt variations in uncertainty, such as sudden overconfidence or high entropy spikes, and provides theoretical guarantees of unbiasedness and consistency. To reduce computational overhead, we incorporate a simple yet effective token-count-based penalty into GUARD. Experimental results demonstrate that GUARD achieves a good balance between text diversity and coherence, while exhibiting substantial improvements in generation speed. In a more nuanced comparison study across different dimensions of text quality, both human and LLM evaluators validated its remarkable performance. Our code is available at https://github.com/YecanLee/GUARD.
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。