paper-with-me

홈 › Papers

Transformers Generalize Linearly

2021-09-24 · Jackson Petty, Robert Frank

Natural language exhibits patterns of hierarchically governed dependencies, in which relations between words are sensitive to syntactic structure rather than linear ordering. While re-current network models often fail to generalize in a hierarchically sensitive way (McCoy et al.,2020) when trained on ambiguous data, the improvement in performance of newer Trans-former language models (Vaswani et al., 2017)on a range of syntactic benchmarks trained on large data sets (Goldberg, 2019; Warstadtet al., 2019) opens the question of whether these models might exhibit hierarchical generalization in the face of impoverished data.In this paper we examine patterns of structural generalization for Transformer sequence-to-sequence models and find that not only do Transformers fail to generalize hierarchically across a wide variety of grammatical mapping tasks, but they exhibit an even stronger preference for linear generalization than comparable recurrent networks

📄 PDF Abstract BibTeX arXiv:2109.12036

Code (1)

clay-lab/transductions pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

In-Context Learning with Representations: Contextual Generalization of Trained Transformers

2024-08-19 · Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely unde…

In-Context Learning

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections

2024-10-22 · Marco Miani, Hrittik Roy, Søren Hauberg

Bayesian deep learning all too often underfits so that the Bayesian prediction is less accurate than a simple point estimate. Uncertainty quantification then comes at the cost of accuracy. For linearized models, the null…

Deep LearningUncertainty Quantification

(How) Can Transformers Predict Pseudo-Random Numbers?

2025-02-14 · Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He 외

Transformers excel at discovering patterns in sequential data, yet their fundamental limitations and learning mechanisms remain crucial topics of investigation. In this paper, we study the ability of Transformers to lear…

Investigating the Indirect Object Identification circuit in Mamba

2024-07-19 · Danielle Ensign, Adrià Garriga-Alonso

How well will current interpretability techniques generalize to future models? A relevant case study is Mamba, a recent recurrent architecture with scaling comparable to Transformers. We adapt pre-Mamba techniques to Mam…

MambaObjectPosition

An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars

2026-06-16 · Vinoth Nandakumar, Qiang Qu, Pramod Thebe, Sakshi Khachariya 외 arxiv

Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and compositional features across layers. …