Break It Down: Evidence for Structural Compositionality in Neural Networks

26 January 2023

Papers citing "Break It Down: Evidence for Structural Compositionality in Neural Networks"

15 / 15 papers shown

Title
Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models Tyler A. Chang Benjamin Bergen 38 0 0 21 Apr 2025
A Complexity-Based Theory of Compositionality Eric Elmoznino Thomas Jiralerspong Yoshua Bengio Guillaume Lajoie CoGe 56 3 0 18 Oct 2024
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models Jack Merullo Carsten Eickhoff Ellie Pavlick 43 12 0 13 Jun 2024
When does compositional structure yield compositional generalization? A kernel theory Samuel Lippl Kim Stachenfeld NAI CoGe 56 5 0 26 May 2024
From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks Jacob Russin Sam Whitman McGrath Danielle J. Williams Lotem Elber-Dorozko AI4CE 59 2 0 24 May 2024
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks Rahul Ramesh Ekdeep Singh Lubana Mikail Khona Robert P. Dick Hidenori Tanaka CoGe 19 6 0 21 Nov 2023
Uncovering Intermediate Variables in Transformers using Circuit Probing Michael A. Lepori Thomas Serre Ellie Pavlick 56 7 0 07 Nov 2023
COLA: A Benchmark for Compositional Text-to-image Retrieval Arijit Ray Filip Radenovic Abhimanyu Dubey Bryan A. Plummer Ranjay Krishna Kate Saenko CoGe VLM 22 34 0 05 May 2023
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 117 314 0 21 Sep 2022
Causal Distillation for Language Models Zhengxuan Wu Atticus Geiger J. Rozner Elisa Kreiss Hanson Lu Thomas F. Icard Christopher Potts Noah D. Goodman 76 25 0 05 Dec 2021
Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks Wang Zhu Peter Shaw Tal Linzen Fei Sha 25 7 0 09 Nov 2021
Quantifying Local Specialization in Deep Neural Networks Shlomi Hod Daniel Filan Stephen Casper Andrew Critch Stuart J. Russell 55 10 0 13 Oct 2021
Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics Prajjwal Bhargava Aleksandr Drozd Anna Rogers 83 101 0 04 Oct 2021
The paradox of the compositionality of natural language: a neural machine translation case study Verna Dankers Elia Bruni Dieuwke Hupkes CoGe 155 75 0 12 Aug 2021
Iterated learning for emergent systematicity in VQA Ankit Vani Max Schwarzer Yucheng Lu Eeshan Gunesh Dhekane Aaron C. Courville 46 19 0 03 May 2021