通过动态调整日志值，让大模型生成更准确且一致的文本。
Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
- 基于最近日志值的谱分析和熵值，自适应调节输出分布。
- 在数学、编程等任务上显著提升准确率，无需修改模型参数。
- 计算轻量，仅在高不确定性时激活，适合实际部署。
基于熵的推理方法在提升大语言模型可靠性方面日益受到关注。然而，许多现有方法（如熵最小化）存在计算开销高、未能有效利用历史标记上下文的问题。为此，我们提出谱日志雕刻（Spectral Logit Sculpting, SLS），一种轻量级的推理时优化方法，通过分析近期日志值的谱特性和熵特性，动态调节令牌分布。SLS维护一个顶K日志值的滑动缓冲区，实时执行奇异值分解（SVD）以识别主导谱方向，并根据熵值与日志间隙统计量自适应地重缩放日志值——仅在不确定性高时激活。无需更新任何模型参数，SLS能有效锐化输出分布，同时保持上下文一致性。在多个公开基准测试中，实验结果表明SLS持续优于现有基线方法，在数学、编码及科学推理任务中实现更高准确率。
原文摘要 · Abstract (English)
Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization techniques, suffer from high computational overhead and fail to leverage historical token context effectively. To address these limitations, we propose Spectral Logit Sculpting (SLS), a lightweight inference-time optimization method that dynamically modulates token distributions using spectral and entropic properties of recent logits. SLS maintains a sliding buffer of top-K logits, performs on-the-fly Singular Value Decomposition (SVD) to identify dominant spectral directions, and adaptively rescales logits based on both entropy and logit gap statistics--only activating when uncertainty is high. Without updating any model parameters, SLS effectively sharpens the output distribution while preserving contextual consistency. Experimental results on multiple public benchmarks demonstrate that SLS consistently outperforms existing baseline methods, achieving superior accuracy in mathematical, coding, and scientific reasoning tasks.
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。