Enhancing Creativity in Large Language Models through Associative Thinking Strategies (2405.06715v1)
Abstract: This paper explores the enhancement of creativity in LLMs like vGPT-4 through associative thinking, a cognitive process where creative ideas emerge from linking seemingly unrelated concepts. Associative thinking strategies have been found to effectively help humans boost creativity. However, whether the same strategies can help LLMs become more creative remains under-explored. In this work, we investigate whether prompting LLMs to connect disparate concepts can augment their creative outputs. Focusing on three domains -- Product Design, Storytelling, and Marketing -- we introduce creativity tasks designed to assess vGPT-4's ability to generate original and useful content. By challenging the models to form novel associations, we evaluate the potential of associative thinking to enhance the creative capabilities of LLMs. Our findings show that leveraging associative thinking techniques can significantly improve the originality of vGPT-4's responses.
- (2012). Associative abilities underlying creativity. Psychology of Aesthetics, Creativity, and the Arts, 6(3), 273.
- Besemer, S. P. (1998). Creative product analysis matrix: testing the model structure and a comparison among products–three novel chairs. Creativity Research Journal, 11(4), 333–346.
- (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877–1901.
- (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712.
- (2023). Art or artifice? large language models and the false promise of creativity. arXiv preprint arXiv:2309.14556.
- Cropley, D. H. (2023). Is ai more creative than humans? chatgpt and the divergent association task.
- (2015). Are creative ideas novel and useful? Psychology of aesthetics, creativity, and the arts, 9(1), 35.
- (2019). The innovator’s dna, updated, with a new preface: Mastering the five skills of disruptive innovators. Harvard Business Press.
- (2023). On the creativity of large language models. arXiv preprint arXiv:2304.00008.
- Gilhooly, K. (2023). Ai vs humans in the aut: simulations to llms. Journal of Creativity, 100071.
- (2023). A confederacy of models: a comprehensive evaluation of llms on creative writing. arXiv preprint arXiv:2310.08433.
- (2015). Novel, effective, whole: Toward a new framework for evaluations of creative products. Journal of Technology and Teacher Education, 23(3), 455–478.
- (2023). Artificial intelligence is more creative than humans: A cognitive science perspective on the current state of generative language models.
- Kahneman, D. (2011). Thinking, fast and slow. macmillan.
- (2009). Beyond big and little: The four c model of creativity. Review of general psychology, 13(1), 1–12.
- Mednick, S. (1962). The associative basis of the creative process. Psychological review, 69(3), 220.
- Michalko, M. (2000). Thinkertoys. Gestión.
- (2021). Show your work: Scratchpads for intermediate computation with language models. arXiv preprint arXiv:2112.00114.
- Rhodes, M. (1961). An analysis of creativity. The Phi delta kappan, 42(7), 305–310.
- (2012). The standard definition of creativity. Creativity research journal, 24(1), 92–96.
- (2004). Causal relationships in creative problem solving: Comparing facilitation interventions for ideation. Journal of management information systems, 20(4), 167–198.
- (2023). The story and the storyteller: Strategic storytelling that gets human attention for entrepreneurs. Business Horizons, 66(3), 347–358.
- (1999). The concept of creativity: Prospects and paradigms. Handbook of creativity, 1(3-15).
- (2022a). Putting gpt-3’s creativity to the (alternative uses) test. arXiv preprint arXiv:2206.08932.
- (2022b). Putting gpt-3’s creativity to the (alternative uses) test. arXiv preprint arXiv:2206.08932.
- (2022). Chain-of-thought prompting elicits reasoning in large language models. , 35, 24824–24837.
- (2023). Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601.
- Pronita Mehrotra (1 paper)
- Aishni Parab (2 papers)
- Sumit Gulwani (55 papers)