English(EN) Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models

新CurioSFT方法增强大型推理模型探索能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-15 04:00

研究人员开发了CurioSFT，一种新颖的大型推理模型监督微调方法，旨在保持其探索能力。与可能导致过度自信和多样性降低的标准SFT不同，CurioSFT使用自探索蒸馏和自适应温度选择来鼓励探索而不遗忘知识。实验表明，CurioSFT在SFT阶段的分布内和分布外任务上均提高了性能，并且这些保留的探索能力转化为后续强化学习阶段的显著收益。 AI

影响该方法通过提高大型推理模型在训练过程中的探索能力，有望使其更加强大和通用。

排序理由该集群包含一篇详细介绍大型语言模型微调新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍大型语言模型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: 85 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Hao Wang, Hao Gu, Hongming Piao, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue, Sirui Han, Yike Guo, Dapeng Wu · 2026-07-15 04:00

面向大型推理模型的熵保持自适应自蒸馏监督微调

arXiv:2602.02244v3 Announce Type: replace-cross Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it of…

本文如何被排名

报道来源 [1]

面向大型推理模型的熵保持自适应自蒸馏监督微调

相关实体

相关话题