Related Experiment Video
Updated: Jul 6, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Humans create more novelty than ChatGPT when asked to retell a story
Fritz Breithaupt1,2, Ege Otenen3,4, Devin R Wright3,4
1Cognitive Science Program, Indiana University Bloomington, 1001 E 10th St, Bloomington, IN, 47405, USA. fbreitha@indiana.edu.
Abstract:
We compare how humans retell stories to how ChatGPT retells stories in chains of three retellings by different people or different accounts on ChatGPT. ChatGPT provides competent summaries of the original narrative texts in one step of retelling. In subsequent retellings few additional changes occur. Human retellers, by contrast, reduce the original text incrementally and by creating 55-60% of novel words and concepts (synsets) at each iteration. The retellings by both ChatGPT and humans show very stable emotion ratings, which is a puzzle for human retellers given the high degree of novel inventions across retellings. ChatGPT maintains more nouns, adjectives, and prepositions and also uses language later acquired in life, while humans use more verbs, adverbs, and negations and use language acquired at a younger age. The results reveal that spontaneous retelling by humans involves ongoing creativity, anchored by emotions, beyond the default probabilistic wording of large language models such as ChatGPT.
Related Concept Videos
Nonconscious Mimicry
Non-equilibrium in the Cell
Genome Size and the Evolution of New Genes
Randomized Experiments
Simple randomization
Simple...
Spontaneity
Genetic Variation
Genes exist in different versions called alleles,...

