ChatGPT is known for its ability to generate text that mirrors human conversation, making it a widely adopted tool for various industries, including digital marketing.
However, a recent to study it questions the model’s ability to generate and understand humor, a key component in engaging and connecting with audiences.
Research by German researchers Sophie Jentzsch and Kristian Kersting suggests that while ChatGPT excels in some areas, it has notable limitations when it comes to generating original humor.
Recycled laughter: the question of originality
A study conducted by Cornell University aims to answer the question: “How does an artificial intelligence model manage humor?”
The researchers examine the originality of AI-generated humor, ChatGPT’s ability to understand and tell jokes, and its ability to detect humor.
The research team states in their report:
“We discovered more than 90% of the samples generated were the same 25 jokes. This recurrence suggests that these jokes are not generated originally, but are learned and memorized explicitly from model training.”
The researchers concluded that these responses were likely learned and memorized during the training of the AI model, indicating a limitation in the model’s ability to generate original humor.
In a report, researchers detail the 10 most frequently generated jokes, including classics like “Why did the scarecrow win an award? Because it was excellent in its field.”
In addition to revealing the complex way in which AI handles humor, the study serves as a warning to people hoping to leverage ChatGPT to create content with a humorous twist.
The implication for digital marketers who rely on AI for content generation is clear, while AI models like ChatGPT can replicate pre-learned patterns to create jokes, originality is lacking.
Despite the repetition, a small number of the responses generated were unique. However, they were largely created by combining elements of different well-known jokes and did not always make sense.
Telling the Joke: Beyond Surface Humor
The study further examined ChatGPT’s ability to explain humor, requiring a deeper understanding of the joke’s structure and implications.
Although the model could deconstruct and explain stylistic elements such as personifications and puns, it showed limitations when faced with more unconventional jokes.
The team observed:
“ChatGPT struggles to explain sequences that don’t fit learned patterns. It won’t indicate when something isn’t funny or doesn’t have a valid explanation.”
In cases where ChatGPT couldn’t identify unfunny jokes, it would come up with plausible-sounding explanations.
For marketers looking to engage their audience through nuanced humor, relying solely on AI may not yield the desired results.
Joke detection: Decoding the punch line
Beyond generating and telling jokes, the research team tested ChatGPT’s ability to detect humor.
They found that while the model can correctly identify jokes based on structure, pun, and theme, it failed to classify a sentence as a joke if it has only one of these characteristics.
This underscores the model’s reliance on learned patterns and lack of a more comprehensive understanding of humor.
What does this mean for marketers?
Although ChatGPT has revolutionized the field of AI-generated content, this research suggests caution in relying on the humor generation model.
The study concludes:
“Although ChatGPT jokes are not newly generated, this does not necessarily remove the capabilities of the system… However, whether an artificial agent is able to understand what it has learned is an exceptionally difficult question.”
As digital marketers look to AI to diversify and expand their content offering, it is essential to understand the limitations and strengths of the model. In the realm of humor, at least for now, human creativity IS irreplaceable.
The research team plans to conduct similar research on recently released AI models such as LLaMa and GPT-NeoX, which promise more insights into the world of computational humor.
Featured image generated by the author via Midjourney.
[ad_2]
Source link
