不训练模型，用记忆库引导自我验证与重生成，提升大模型输出准确率。
A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
- 用离线构建的对比记忆库指导推理验证和重新生成
- 在9个基准上优于已有方法，计算开销低
- 适合追求高精度且不想训练的用户
自验证引导的自我改进已成为提升大语言模型输出准确性的有前景方法。然而现有方法在推理效率与准确性之间存在权衡：迭代验证修正计算成本高且易陷入错误推理；最佳N选一需大量采样，未解决模型内部缺陷。我们提出一种无需训练的再生范式，利用离线构建的对比反射记忆（RM）提供修正指引，同时从头重生成有助于摆脱错误推理。推理时，方法先进行RM引导的自验证，再执行一次RM引导的重生成，避免了迭代修正和多样本选择。我们在涵盖算法、推理、符号及领域特定任务的九个基准上评估该方法，覆盖小规模与大规模模型。实验结果表明，该方法在保持低计算成本的同时，优于先前方法。
原文摘要 · Abstract (English)
Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy: iterative verification-rectification is computationally expensive and prone to being trapped in faulty reasoning, while best-of-N selection requires extensive sampling without addressing internal model flaws. We propose a training-free regeneration paradigm that leverages an offline-curated contrastive Reflection Memory (RM) to provide corrective guidance, while regenerating from scratch helps break out of faulty reasoning. At inference time, the method performs RM-guided self-verification followed by a single RM-guided regeneration, avoiding both iterative correction and multi-sample selection. We evaluated our method on nine benchmarks that span algorithmic, reasoning, symbolic, and domain-specific tasks in both small- and large-scale LLMs. Experiment results show that our method outperforms prior methods while maintaining low computational cost.
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。