预训练大模型能自发学习多种不确定性，提升判断准确性。
Pretrained LLMs Learn Multiple Types of Uncertainty
- 将不确定性视为隐空间中的线性概念，无需额外训练即可捕捉。
- 模型能区分多种不确定性类型，分别适用于不同任务的正确性预测。
- 指令微调或[IDK]令牌调优可统一不确定性类型，改善判断表现。
大型语言模型虽能掌握现实世界知识，在下游任务中表现优异，但仍易产生幻觉，生成不实文本。本文研究预训练大模型在未显式训练的情况下对不确定性的捕捉能力。结果显示，若将不确定性视为模型隐空间中的线性概念，即使仅经过预训练，也能被有效捕捉。进一步发现，尽管反直觉，模型实际上能识别多种不同类型不确定性，每种均有助于特定任务或基准的正确性预测。深入分析表明，我们的纠正预测与模型通过用词回避错误信息的能力存在相关性，且模型规模扩大对不确定性捕捉无显著影响。最后，我们提出通过指令微调或[IDK]令牌调优，将多种不确定性统一为单一形式，有助于提升模型的正确性预测能力。
原文摘要 · Abstract (English)
Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit unwanted and factually incorrect text. In this work, we study how well LLMs capture uncertainty, without explicitly being trained for that. We show that, if considering uncertainty as a linear concept in the model's latent space, it might indeed be captured, even after only pretraining. We further show that, though unintuitive, LLMs appear to capture several different types of uncertainty, each of which can be useful to predict the correctness for a specific task or benchmark. Furthermore, we provide in-depth results such as demonstrating a correlation between our correction prediction and the model's ability to abstain from misinformation using words, and the lack of impact of model scaling for capturing uncertainty. Finally, we claim that unifying the uncertainty types as a single one using instruction-tuning or [IDK]-token tuning is helpful for the model in terms of correctness prediction.
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。