49 citations · 51 across the 5 of their papers we have counts for
5 papers · 1 filter
Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication
Tom Kouwenhoven, Max Peeperkorn, Roy de Kleijn +1
Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases…
Searching for Structure: Investigating Emergent Communication with Large Language Models
Tom Kouwenhoven, Max Peeperkorn, Tessa Verhoef
Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape lingui…
The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication
Tom Kouwenhoven, Max Peeperkorn, Bram van Dijk +1
Natural language has the universal properties of being compositional and grounded in reality. The emergence of linguistic properties is often investigated through simulations of em…
Is Temperature the Creativity Parameter of Large Language Models?
Max Peeperkorn, Tom Kouwenhoven, Dan Brown +1
Large language models (LLMs) are applied to all sorts of creative tasks, and their outputs vary from beautiful, to peculiar, to pastiche, into plain plagiarism. The temperature par…
Bits of Grass: Does GPT already know how to write like Whitman?
Piotr Sawicki, Marek Grzes, Fabricio Goes +3
This study examines the ability of GPT-3.5, GPT-3.5-turbo (ChatGPT) and GPT-4 models to generate poems in the style of specific authors using zero-shot and many-shot prompts (which…