Summary of Forma Mentis Networks Predict Creativity Ratings Of Short Texts Via Interpretable Artificial Intelligence in Human and Gpt-simulated Raters, by Edith Haim et al.
Forma mentis networks predict creativity ratings of short texts via interpretable artificial intelligence in human and GPT-simulated raters
by Edith Haim, Natalie Fischer, Salvatore Citraro, Giulio Rossetti, Massimo Stella
First submitted to arxiv on: 30 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach uses textual forma mentis networks (TFMN) to extract semantic/syntactic associations and emotional features from approximately one thousand human-generated stories and those created by GPT3.5. The study employs Explainable Artificial Intelligence (XAI) to investigate whether features related to Mednick’s associative theory of creativity can explain creativity ratings assigned by humans and GPT-3.5. Using XGBoost, the researchers examine three scenarios: human ratings of human stories, GPT-3.5 ratings of human stories, and GPT-3.5 ratings of GPT-generated stories. The findings reveal significant differences between GPT-3.5’s ratings and human ratings, with feature patterns identified using XAI methods. Feature importance analysis shows that network features are more predictive for human creativity ratings but also for GPT-3.5’s ratings of human stories. This study highlights the need for caution when using GPT-3.5 to assess and generate creative content, as it does not yet capture the nuanced complexity characterising human creativity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GPT-3.5 is a powerful AI tool that can create stories like humans do. Researchers wanted to see if this AI could understand what makes a story creative. They used special techniques called textual forma mentis networks and Explainable Artificial Intelligence to study GPT-3.5’s understanding of creativity. The results showed that GPT-3.5 has its own way of thinking about creativity, which is different from how humans think. This means we should be careful when using GPT-3.5 to create stories, because it might not capture the same level of creativity as a human. |
Keywords
» Artificial intelligence » Gpt » Xgboost
