Reconstruction Probing
We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction -- the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration
Spatial transcriptomics (ST) enables the simultaneous profiling of gene expression and tissue morphology, creating an opportunity to learn multimodal representations capturing shared morpho-transcriptomic structure. Howe…
Representation LearningKeypoint Aware Masked Image Modelling
SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perform sub-optimally when used for linear pro…
Contrastive LearningSelf-Supervised Video Transformers for Isolated Sign Language Recognition
This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR). We consider four recently introduced transformer-based approaches to self-supervised learning fr…
Self-Supervised LearningSign Language RecognitionBeyond Decodability: Reconstructing Language Model Representations with an Encoding Probe
Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach…
Fast and Lightweight Backdoor Detection via Head Random Probing
Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gradients, or iterative trigger reconstruction, leading to high comput…