估算语言模型罕见输出概率，提升对极端情况的可靠性
Estimating the Probabilities of Rare Outputs in Language Models
- 用重要性采样和激活外推法估算极低概率输出
- 重要性采样优于传统采样，能更准估计罕见行为概率
- 适合关注模型鲁棒性与安全性的研究者
我们研究低概率估计问题：给定一个机器学习模型和形式化输入分布，如何估计模型输出某一二值属性的概率，即使该概率极低无法通过随机采样获得？这一问题源于改善最坏情况性能的需求，而分布偏移可能使此类情况更可能发生。本文在小型Transformer语言模型的argmax采样背景下研究该问题，比较了两种方法：重要性采样（搜索引发罕见输出的输入）与激活外推（基于模型logits拟合概率分布并外推）。结果表明，重要性采样优于激活外推，两者均显著优于朴素采样。最后，我们指出最小化不利行为的概率估计可推广对抗训练，并强调需发展新方法以提供更强的最坏情况性能保证。
原文摘要 · Abstract (English)
We consider the problem of low probability estimation: given a machine learning model and a formally-specified input distribution, how can we estimate the probability of a binary property of the model's output, even when that probability is too small to estimate by random sampling? This problem is motivated by the need to improve worst-case performance, which distribution shift can make much more likely. We study low probability estimation in the context of argmax sampling from small transformer language models. We compare two types of methods: importance sampling, which involves searching for inputs giving rise to the rare output, and activation extrapolation, which involves extrapolating a probability distribution fit to the model's logits. We find that importance sampling outperforms activation extrapolation, but both outperform naive sampling. Finally, we explain how minimizing the probability estimate of an undesirable behavior generalizes adversarial training, and argue that new methods for low probability estimation are needed to provide stronger guarantees about worst-case performance.
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。