5 papers · 1 filter
LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks
Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama +3
The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they cannot move beyond statistical pattern m…
Self-reported archetypes and behavioral failures in Large Language Models
Tabia Tanzin Prama, Calla Glavin Beauregard, Christopher M. Danforth +1
Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property of training, these systems ex…
Statistical laws and linguistics differ in naturalistic video and fictional conversations
Ashley M. A. Fehr, Calla G. Beauregard, Julia Witte Zimmerman +4
Conversation is a cornerstone of social connection and is linked to well-being outcomes. Conversations vary widely in type with some portion generating complex, dynamic stories. On…
A suite of allotaxonometric tools for the comparison of complex systems using rank-turbulence divergence
Jonathan St-Onge, Ashley M. A. Fehr, Carter Ward +6
Describing and comparing complex systems requires principled, theoretically grounded tools. Built around the phenomenon of type turbulence, allotaxonographs provide map-and-list vi…
Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning
Julia Witte Zimmerman, Denis Hudon, Kathryn Cramer +9
Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet i…