arXiv cs.CL· Giannis Daras, Marios Papachristou, Adam Klivans, Antonio Torralba, Constantinos Daskalakis·· 23 小时前AI 评分34
Ambient LLMs:通过温度匹配实现数据高效监督微调
Ambient LLMs: Data-Efficient Supervised Fine-tuning via Temperature Matching
AI 导读
研究者提出 Ambient SFT,用预训练模型的“冻结”版本作为噪声教师,要求微调模型的高温条件分布与预训练模型的高温版本在粗粒度上匹配,温度超参数控制对预训练模型的信任程度,T→∞ 退回常规 SFT,T=1 则为知识蒸馏。该方法在领域适应、指令微调和推理任务上均优于标准 SFT,平均相对提升最高达 21%。
正文 · 原文
Abstract:Collecting large-scale, diverse, and high-quality post-training datasets for autoregressive language models is challenging. Consequently, Supervised Fine-Tuning (SFT) is typically applied to datasets significantly smaller than those used for pre-training, which leads to overfitting and the catastrophic forgetting of the tails of the data distribution. To prevent this collapse, we introduce Ambient SFT, a principled framework for leveraging imperfect predictions to augment the fine-tuning set. In our method, a "frozen" version of the pre-trained model serves as a noisy teacher that the fine-tuned model must match at a coarse level. In particular, we require that the high-temperature versions of the conditional distributions produced by the post-training model should match the high-temperature versions of the pre-training ones. The temperature hyperparameter controls the level of trust in the pre-trained model, with the limit $T\to \infty$ reverting back to regular SFT and $T=1$ to knowledge distillation. We demonstrate that our approach outperforms standard SFT across domain adaptation, instruction-tuning, and reasoning, leading for up to $21\%$ average relative improvement to standard SFT.
| Comments: | Work in progress |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.23229 [cs.LG] |
| (or arXiv:2611.23229v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23229 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Giannis Daras [view email]
[v1]
Tue, 17 Nov 2026 18:59:37 UTC (171 KB)
来源:arXiv cs.CL · arxiv.org