10 papers
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…
The queer Hero versus the Fool bias of the queer trait: An archetypometric analysis of the collective portrayal of queerness in fictional stories
Ashley M. A. Fehr, Calla Glavin Beauregard, Julia Witte Zimmerman +4
Visibility in media is pivotal for identity development and for broadening societal views of gender and sexuality. Queer representation has increased in recent years, yet damaging…
Buffy versus Bella: An archetypometric analysis and comparison
Calla Glavin Beauregard, Julia Witte Zimmerman, Ashley M. A. Fehr +6
Fictional stories and characters embody and encode social norms, and their study is a powerful tool through which to understand culture and society. Vampire stories and folklore, i…
Archetypes and gender in fiction: A data-driven mapping of gender stereotypes in stories
Calla Glavin Beauregard, Julia Witte Zimmerman, Ashley M. A. Fehr +3
Fictional character representations reflect social norms and biases. For example, women are relatively underrepresented in television and film, irrespective of genre, and are frequ…
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…
Detecting sub-populations in online health communities: A mixed-methods exploration of breastfeeding messages in BabyCenter Birth Clubs
Calla Beauregard, Parisa Suchdev, Ashley M. A. Fehr +7
Parental stress is a nationwide health crisis according to the U.S. Surgeon General's 2024 advisory. To allay stress, expecting parents seek advice and share experiences in a varie…
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…
Hollywood's misrepresentation of death: A comparison of overall and by-gender mortality causes in film and the real world
Calla Beauregard, Christopher M. Danforth, Peter Sheridan Dodds
The common phrase 'representation matters' asserts that media has a measurable and important impact on civic society's perception of self and others. The representation of health i…