Characterizing Intrinsic Compositionality in Transformers with Tree Projections

2 November 2022

Papers citing "Characterizing Intrinsic Compositionality in Transformers with Tree Projections"

6 / 6 papers shown

Title
Sneaking Syntax into Transformer Language Models with Tree Regularization Ananjan Nandi Christopher D. Manning Shikhar Murty 74 0 0 28 Nov 2024
Geometric Signatures of Compositionality Across a Language Model's Lifetime Jin Hwa Lee Thomas Jiralerspong Lei Yu Yoshua Bengio Emily Cheng CoGe 84 0 0 02 Oct 2024
What does the Knowledge Neuron Thesis Have to do with Knowledge? Jingcheng Niu Andrew Liu Zining Zhu Gerald Penn 48 30 0 03 May 2024
Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings Yichen Jiang Xiang Zhou Mohit Bansal 32 1 0 09 Feb 2024
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction Pratyusha Sharma Jordan T. Ash Dipendra Kumar Misra LRM 15 78 0 21 Dec 2023
Compositional Fusion of Signals in Data Embedding Zhijin Guo Zhaozhen Xu Martha Lewis N. Cristianini 11 0 0 18 Nov 2023