2.6k citations · 4k across the 31 of their papers we have counts for
7 papers · 1 filter
Tolerance Principle and Small Language Model Learning
Adam E. Friedman, Stevan Harnad, Rushen Shi
Modern language models like GPT-3, BERT, and LLaMA require massive training data, yet with sufficient training they reliably learn to distinguish grammatical from ungrammatical sen…
Language Writ Large: LLMs, ChatGPT, Grounding, Meaning and Understanding
Stevan Harnad
Apart from what (little) OpenAI may be concealing from us, we all know (roughly) how ChatGPT works (its huge text database, its statistics, its vector representations, and their hu…
The Latent Structure of Dictionaries
Philippe Vincent-Lamarre, Alexandre Blondin Massé, Marcos Lopes +3
How many words (and which ones) are sufficient to define all other words? When dictionaries are analyzed as directed graphs with links from defining words to defined words, they re…
Hidden Structure and Function in the Lexicon
Olivier Picard, Mélanie Lord, Alexandre Blondin-Massé +3
How many words are needed to define all the words in a dictionary? Graph-theoretic analysis reveals that about 10% of a dictionary is a unique Kernel of words that define one anoth…
Hierarchies in Dictionary Definition Space
Olivier Picard, Alexandre Blondin-Masse, Stevan Harnad +3
A dictionary defines words in terms of other words. Definitions can tell you the meanings of words you don't know, but only if you know the meanings of the defining words. How many…
What It Feels Like To Hear Voices: Fond Memories of Julian Jaynes
Stevan Harnad
Julian Jaynes's profound humanitarian convictions not only prevented him from going to war, but would have prevented him from ever kicking a dog. Yet according to his theory, not o…