Turing Jest
Distributional Semantics and One‐Line Jokes
Bibliographic Data
| ID | 7150350 |
|---|---|
| Authors | Sean Trott (0000-0002-6003-3731, Department of Cognitive Science University of California San Diego, corresponding author), Drew E Walker (Department of Cognitive Science University of California San Diego), Drew Walker (University of California San Diego, corresponding author), Samuel M Taylor (Department of Cognitive Science University of California San Diego), Seana Coulson (0000-0003-1246-9394, Department of Cognitive Science University of California San Diego) |
| Year | 2025 |
| Volume | 49 |
| Issue | 5 |
| Pages | e70066-e70066 |
| Publication date | 2025-05-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Cognitive Science (JOURNAL) |
| Journal identifiers | ISSN: 0364-0213 • E-ISSN: 1551-6709 |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.1111/cogs.70066 |
| PMID | 40396401 |
| OpenAlex | W4410565378 |
| Language | EN |
| References cited | 76 |
Humor is an essential aspect of human experience, yet surprisingly, little is known about how we recognize and understand humorous utterances. Most theories of humor emphasize the role of incongruity detection and resolution (e.g., frame‐shifting), as well as cognitive capacities like Theory of Mind and pragmatic reasoning. In multiple preregistered experiments, we ask whether and to what extent exposure to purely linguistic input can account for the human ability to recognize one‐line jokes and identify their entailments. We find that GPT‐3, a large language model (LLM) trained on only language data, exhibits above‐chance performance in tasks designed to test its ability to detect, appreciate, and comprehend jokes. In exploratory work, we also find above‐chance performance in humor detection and comprehension in several open‐source LLMs, such as Llama‐3 and Mixtral. Although all LLMs tested fall short of human performance, both humans and LLMs show a tendency to misclassify nonjokes with surprising endings as jokes. Results suggest that LLMs are remarkably adept at some tasks involving one‐line jokes, but reveal key limitations of distributional approaches to meaning
Cognition · Cognitive psychology · Comprehension · Linguistics · Computer Science · Educational Methods and Analysis · Humor Studies and Applications · Language, Metaphor, and Cognition · Psychology · Social Psychology
Semantic Leaps
Transformers
Humour as emotion regulation
Dissociating language and thought in large language models
Laughter among Colleagues †
A Two-Stage Model for the Appreciation of Jokes and Cartoons
Climbing towards NLU
Using cognitive psychology to understand GPT-3
Jeer Pressure
The weirdest people in the world?
Semantic Mechanisms of Humor
Large Language Models and the Wisdom of Small Crowds
Frame-Shifting in Humor and Irony
Investigating the distribution of some (but not all) implicatures using corpora and web-based methods
Finding comfort in a joke
Disclosure humor and distortion humor
Script theory revis(it)ed
Looking back
Script oppositions and logical mechanisms
The influence of empathizing and systemizing on humor processing
Humor’s role in married life
Do I amuse you? Asymmetric predictors for humor appreciation and humor production
Human Language Understanding & Reasoning
Jokes and their Relation to the Unconscious 1905
Gender stereotypes are reflected in the distributional structure of 25 languages
A frame-theoretical analysis of verbal humor
Distributional Structure
| Highly cited | No |
|---|