总结大模型推理时自我优化的三大方法，助力提升生成质量。
A Survey on LLM Inference-Time Self-Improvement
- 按解码、上下文、模型协作三类梳理推理优化思路
- 系统整理近年相关研究，构建完整分类体系
- 适合关注大模型推理效率与效果的研究者阅读
通过增加测试时计算量来提升大模型推理性能的技术近年来备受关注。本文从三个视角综述大模型推理时自我优化的现状：独立自我优化，侧重于通过解码或采样方法改进；上下文感知自我优化，利用额外上下文或数据存储；模型辅助自我优化，通过模型间协作实现提升。文章全面回顾了近期相关研究，提出深入的分类体系，并讨论挑战与局限，为未来研究提供洞见。
原文摘要 · Abstract (English)
Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time Self-Improvement from three different perspectives: Independent Self-improvement, focusing on enhancements via decoding or sampling methods; Context-Aware Self-Improvement, leveraging additional context or datastore; and Model-Aided Self-Improvement, achieving improvement through model collaboration. We provide a comprehensive review of recent relevant studies, contribute an in-depth taxonomy, and discuss challenges and limitations, offering insights for future research.
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。