How do large language models (LLMs) obtain their answers? The ability to
explain and control an LLM's reasoning process is key for reliability,
transparency, and future model developments. We propose SelfIE
(Self-Interpretation of Embeddings), a framework that enables LLMs to interpret
their own embeddings in natural language by leveraging their ability to respond
inquiry about a given passage. Capable of interpreting open-world concepts in
the hidden embeddings, SelfIE reveals LLM internal reasoning in cases such as
making ethical decisions, internalizing prompt injection, and recalling harmful
knowledge. SelfIE's text descriptions on hidden embeddings also open up new
avenues to control LLM reasoning. We propose Supervised Control, which allows
editing open-ended concepts while only requiring gradient computation of
individual layer. We extend RLHF to hidden embeddings and propose Reinforcement
Control that erases harmful knowledge in LLM without supervision targets.

通过使用自然语言解释嵌入，SelfIE 可以揭示大型语言模型的内部推理过程，从而实现对其推理过程的解释和控制，进而提高可靠性、透明度和未来模型发展的能力。另外，我们提出了监督控制和强化控制的方法，分别用于编辑开放性概念和消除有害知识。

自我解读：大型语言模型嵌入的自我解释

SelfIE: Self-Interpretation of Large Language Model Embeddings

We introduce a pretraining technique called Selfie, which stands for SELFie
supervised Image Embedding. Selfie generalizes the concept of masked language
modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by
making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given
masked-out patches in an input image, our method learns to select the correct
patch, among other "distractor" patches sampled from the same image, to fill in
the masked location. This classification objective sidesteps the need for
predicting exact pixel values of the target patches. The pretraining
architecture of Selfie includes a network of convolutional blocks to process
patches followed by an attention pooling network to summarize the content of
unmasked patches before predicting masked ones. During finetuning, we reuse the
convolutional weights found by pretraining. We evaluate Selfie on three
benchmarks (CIFAR-10, ImageNet 32 x 32, and ImageNet 224 x 224) with varying
amounts of labeled data, from 5% to 100% of the training sets. Our pretraining
method provides consistent improvements to ResNet-50 across all settings
compared to the standard supervised training of the same network. Notably, on
ImageNet 224 x 224 with 60 examples per class (5%), our method improves the
mean accuracy of ResNet-50 from 35.6% to 46.7%, an improvement of 11.1 points
in absolute accuracy. Our pretraining method also improves ResNet-50 training
stability, especially on low data regime, by significantly lowering the
standard deviation of test accuracies across different runs.

本文介绍了一种名为 Selfie 的预训练技术，其可以通过对图像进行掩蔽语言建模来进行图像嵌入，并且可以很好地适用于低数据情况下的 ResNet-50 图像分类器的训练。