研究人员开发了一种新方法，用于在应用特定约束时提高大型语言模型输出的准确性并减少偏差。所提出的方法称为概率全局约束解码 (P-GCD)，它利用具有源自有限自动机的 novel proposal distributions 的顺序蒙特卡洛方法。该技术旨在克服现有局部约束解码方法的局限性，这些方法可能导致有偏抽样和性能下降。 AI
影响 增强了 LLM 在函数调用和 SQL 生成等结构化数据任务中的可靠性。
排序理由 这是一篇详细介绍改进 LLM 输出新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.01926v1 Announce Type: new Abstract: Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints by myopically masking out next tokens, resulting in …
Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints by myopically masking out next tokens, resulting in biased sampling and degradation in performance. …