English(EN) Finetuning with Sampling: SFT Learns Better Than You Think

新的采样方法提升了 LLM 的监督微调效果

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员开发了一种新的采样算法，可以增强大型语言模型（LLM）的监督微调（SFT）。这种马尔可夫链蒙特卡洛（MCMC）方法将离策略数据轨迹转换为更符合同策略学习的方式，使 SFT 在泛化能力上能够媲美甚至超越传统的强化学习技术，并减少灾难性遗忘。该方法在科学技能获取和数学推理等各种任务中表现强劲，并将采样视为模型后训练的一种通用基元。 AI

影响通过提高微调效率和性能来增强 LLM 的能力，有望带来更强大、更多功能的模型。

排序理由关于 LLM 微调新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于 LLM 微调新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Aayush Karan, Sitan Chen, Yilun Du · 2026-10-02 04:00

采样微调：SFT 比你想象的学得更好

arXiv:2610.02140v1 Announce Type: cross Abstract: Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and reinforcement learning (RL) to this end. Conventional wisdom dictates that RL enab…

本文如何被排名

报道来源 [1]

采样微调：SFT 比你想象的学得更好

相关实体

相关话题