Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics
Not on the map. Why?
Abstract (arXiv)
Large language models are not detailed models of human linguistic processing. They are, however, extremely successful at their primary task: providing a model for language. For this reason and because there are no animal models for language, large language models are important in psycholinguistics: they are useful as a practical tool, as an illustrative comparative, and philosophically, as a basis for recasting the relationship between language and thought.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 60 of its 369 references that are in the map. First posted on arXiv 28 Feb 2023.
Builds on
60 of 369 references.
References · 60
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2013Intriguing properties of neural networkscited by 5,114
- 2020Shortcut Learning in Deep Neural Networkscited by 1,928
- 2019Invariant Risk Minimizationcited by 1,832
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
- 2017Dynamic Routing Between Capsulescited by 689
38 more
- 2016End-to-end Optimized Image Compressioncited by 673
- 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
- 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
- 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
- 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 350
- 2018Understanding disentangling in β-VAEcited by 332
- 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
- 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
- 2018Targeted Syntactic Evaluation of Language Modelscited by 239
- 2018Colorless green recurrent networks dream hierarchicallycited by 210
- 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
- 2021Partial success in closing the gap between human and machine visioncited by 185
- 2018A mathematical theory of semantic development in deep neural networkscited by 182
- 2020Liquid Time-constant Networkscited by 160
- 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 137
- 2021How to represent part-whole hierarchies in a neural networkcited by 123
- 2017The Consciousness Priorcited by 105
- 2018Learning long-range spatial dependencies with horizontal gated-recurrent unitscited by 98
- 2020Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Futurecited by 83
- 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
- 2020Self-supervised learning through the eyes of a childcited by 61
- 2022Harmonizing the object recognition strategies of deep neural networks with humanscited by 59
- 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
- 2022The neuroconnectionist research programmecited by 47
- 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
- 2018Cognitive computational neurosciencecited by 43
- 2018Learning to Play with Intrinsically-Motivated Self-Aware Agentscited by 34
- 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
- 2018Humans can decipher adversarial imagescited by 31
- 2019Disentangling neural mechanisms for perceptual groupingcited by 28
- 2018Task-Driven Convolutional Recurrent Models of the Visual Systemcited by 27
- 2020Recurrent neural circuits for contour detectioncited by 23
- 2021Capturing the objects of vision with neural networkscited by 21
- 2018Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealedcited by 16
- 2018Distinct patterns of syntactic agreement errors in recurrent networks and humanscited by 13
- 2021Understanding the computational demands underlying visual reasoningcited by 13
- 2017Understanding trained CNNs by indexing neuron selectivitycited by 12
- 2017Fixing a Broken ELBOcited by 12
50 most cited of 60 All 60 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.