Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans

14 October 2021

Papers citing "Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans"

8 / 8 papers shown

Title
Can Transformers Do Enumerative Geometry? Baran Hashemi Roderic G. Corominas Alessandro Giacchetto 39 2 0 27 Aug 2024
Language acquisition: do children and language models follow similar learning stages? Linnea Evanson Yair Lakretz J. King 27 26 0 06 Jun 2023
Dissociating language and thought in large language models Kyle Mahowald Anna A. Ivanova I. Blank Nancy Kanwisher J. Tenenbaum Evelina Fedorenko ELM ReLM 25 209 0 16 Jan 2023
Probing for Incremental Parse States in Autoregressive Language Models Tiwalayo Eisape Vineet Gangireddy R. Levy Yoon Kim 25 11 0 17 Nov 2022
State-of-the-art generalisation research in NLP: A taxonomy and review Dieuwke Hupkes Mario Giulianelli Verna Dankers Mikel Artetxe Yanai Elazar ... Leila Khalatbari Maria Ryskina Rita Frieske Ryan Cotterell Zhijing Jin 114 93 0 06 Oct 2022
Using cognitive psychology to understand GPT-3 Marcel Binz Eric Schulz ELM LLMAG 250 440 0 21 Jun 2022
Transformers Generalize Linearly Jackson Petty Robert Frank AI4CE 216 16 0 24 Sep 2021
Can RNNs learn Recursive Nested Subject-Verb Agreements? Yair Lakretz T. Desbordes J. King Benoît Crabbé Maxime Oquab S. Dehaene 160 19 0 06 Jan 2021