Skip to main content
Springer Nature Link
Log in

Generative AI Can Be Creative Too

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2024)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14951))

Included in the following conference series:

  • 883 Accesses

Abstract

Large Language Models (LLMs) have significantly influenced everyday computational tasks and the pursuit of Artificial General Intelligence (AGI). However, their creativity is limited by the conventional data they learn from, particularly lacking in novelty. To enhance creativity in LLMs, this paper introduces an innovative approach using the Learning Intelligent Decision Agent (LIDA) cognitive architecture. We describe and implement a multimodal vector embeddings-based LIDA in this paper. A LIDA agent from this implementation is used to demonstrate our proposition to make generative AI more creative, specifically making it more novel. By leveraging episodic memory and attention, the LIDA-based agent can relate memories of recent unrelated events to solve current problems with novelty. Our approach incorporates a neuro-symbolic implementation of a LIDA agent that assists in generating creative ideas while illuminating a prompting technique for LLMs to make them more creative. Comparing responses from a baseline LLM and our LIDA-enhanced agent indicates an improvement in the novelty of the ideas generated.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The responses from the agent, here and throughout the paper, are clipped using triple dots (‘…’) wherever needed to provide necessary context for creativity while removing irrelevant text.

References

  1. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2017)

    Google Scholar 

  2. Achiam, J., et al.: GPT-4 technical report. arXiv Prepr. arXiv:2303.08774 (2023)

  3. Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)

    Google Scholar 

  4. Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with GPT-4. arXiv Prepr. arXiv:2303.12712 (2023)

  5. Kosinski, M.: Theory of mind may have spontaneously emerged in large language models. arXiv Prepr. arXiv:2302.02083, vol. 4, p. 169 (2023)

  6. Romero, O.J., Zimmerman, J., Steinfeld, A., Tomasic, A.: Synergistic integration of large language models and cognitive architectures for robust AI: an exploratory analysis. Presented at the Proceedings of the AAAI Symposium Series (2023)

    Google Scholar 

  7. Park, J.S., O’Brien, J., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: Interactive simulacra of human behavior. Presented at the Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (2023)

    Google Scholar 

  8. Karimi, P., Rezwana, J., Siddiqui, S., Maher, M.L., Dehbozorgi, N.: Creative sketching partner: an analysis of human-AI co-creativity. Presented at the Proceedings of the 25th International Conference on Intelligent User Interfaces (2020)

    Google Scholar 

  9. Lawton, T., Ibarrola, F.J., Ventura, D., Grace, K.: Drawing with reframer: emergence and control in co-creative AI. Presented at the Proceedings of the 28th International Conference on Intelligent User Interfaces (2023)

    Google Scholar 

  10. Torrance, E.P.: Torrance Tests of Creative Thinking (2012). https://doi.apa.org/doi/10.1037/t05532-000. https://doi.org/10.1037/t05532-000

  11. Zhao, Y., et al.: Assessing and Understanding Creativity in Large Language Models (2024). http://arxiv.org/abs/2401.12491. https://doi.org/10.48550/arXiv.2401.12491

  12. Franklin, S., et al.: A LIDA cognitive model tutorial. Biol. Inspired Cogn. Archit. 16, 105–130 (2016)

    Google Scholar 

  13. Franklin, S.: Artificial Minds. MIT Press, Cambridge (1997)

    Book  Google Scholar 

  14. Franklin, S., Madl, T., D’Mello, S., Snaider, J.: LIDA: a systems-level architecture for cognition, emotion, and learning. IEEE Trans. Auton. Ment. Dev. 6, 19–41 (2014). https://doi.org/10.1109/TAMD.2013.2277589

    Article  Google Scholar 

  15. Dong, D.: Enabling an autonomous agent sharing its minds, describing its conscious contents. Cogn. Syst. Res. 80, 103–109 (2023)

    Article  Google Scholar 

  16. Dong, D., Franklin, S.: A new action execution module for the learning intelligent distribution agent (LIDA): the sensory motor system. Cogn. Comput. 7, 1–17 (2015). https://doi.org/10.1007/s12559-015-9322-3

    Article  Google Scholar 

  17. Khayi, N.A., Franklin, S.: Initiating language in LIDA: learning the meaning of vervet alarm calls. Biol. Inspired Cogn. Archit. 23, 7–18 (2018)

    Google Scholar 

  18. Kronsted, C., Neemeh, Z.A., Kugele, S., Franklin, S.: Modeling long-term intentions and narratives in autonomous agents. J. Artif. Intell. Conscious. 8, 229–265 (2021)

    Article  Google Scholar 

  19. McCall, R.J., Franklin, S., Faghihi, U., Snaider, J., Kugele, S.: Artificial motivation for cognitive software agents. J. Artif. Gen. Intell. 11, 38–69 (2020)

    Article  Google Scholar 

  20. Dong, D., Franklin, S., Agrawal, P.: Estimating human movements using memory of errors. Procedia Comput. Sci. 71, 1–10 (2015). https://doi.org/10.1016/j.procs.2015.12.174

    Article  Google Scholar 

  21. Baars, B.J.: A Cognitive Theory of Consciousness. Cambridge University Press, New York (1988)

    Google Scholar 

  22. Baars, B.J.: The conscious access hypothesis: origins and recent evidence. Trends Cogn. Sci. 6, 47–52 (2002)

    Article  Google Scholar 

  23. Madl, T., Baars, B.J., Franklin, S.: The timing of the cognitive cycle. PLoS ONE 6, e14803 (2011). https://doi.org/10.1371/journal.pone.0014803

    Article  Google Scholar 

  24. Glenberg, A.M.: What memory is for: creating meaning in the service of action. Behav. Brain Sci. 20, 41–50 (1997). https://doi.org/10.1017/S0140525X97470012

    Article  Google Scholar 

  25. Baddeley, A.D., Hitch, G.: Working memory. In: Bower, G.H. (ed.) Psychology of Learning and Motivation, pp. 47–89. Academic Press (1974). https://doi.org/10.1016/S0079-7421(08)60452-1

  26. Varela, F.J., Thompson, E.T., Rosch, E.: The Embodied Mind: Cognitive Science and Human Experience. MIT Press, Cambridge (1992)

    Google Scholar 

  27. Ramamurthy, U., Franklin, S., Agrawal, P.: Self-system in a model of cognition. Int. J. Mach. Conscious. 04, 325–333 (2012). https://doi.org/10.1142/S1793843012400185

    Article  Google Scholar 

  28. Ryan, K., Agrawal, P., Franklin, S.: The pattern theory of self in artificial general intelligence: a theoretical framework for modeling self in biologically inspired cognitive architectures. Cogn. Syst. Res. 62, 44–56 (2020). https://doi.org/10.1016/j.cogsys.2019.09.018

    Article  Google Scholar 

  29. Conway, M.A.: Sensory–perceptual episodic memory and its context: autobiographical memory. Philos. Trans. R. Soc. Lond. B Biol. Sci. 356, 1375–1384 (2001). https://doi.org/10.1098/rstb.2001.0940

    Article  Google Scholar 

  30. Moulton, S.T., Kosslyn, S.M.: Imagining predictions: mental imagery as mental emulation. Philos. Trans. R. Soc. B Biol. Sci. 364, 1273–1280 (2009)

    Google Scholar 

  31. Snaider, J., Franklin, S.: Vector LIDA. Procedia Comput. Sci. 41, 188–203 (2014)

    Google Scholar 

  32. Agrawal, P., Franklin, S., Snaider, J.: Sensory memory for grounded representations in a cognitive architecture. In: Proceedings of the Sixth Annual Conference on Advances in Cognitive Systems (ACS Poster Collection), pp. 1–18 (2018)

    Google Scholar 

  33. Cropley, A.J.: Creativity and cognition: producing effective novelty. Roeper Rev. 21, 253–260 (1999). https://doi.org/10.1080/02783199909553972

    Article  Google Scholar 

  34. McCall, R., Snaider, J., Franklin, S.: Sensory and perceptual scene representation (2010). https://ccrg.cs.memphis.edu/assets/papers/2010/Scene_Representation_v20.doc

  35. Llama 2: Open Foundation and Fine-Tuned Chat Models | Research - AI at Meta. https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/. Accessed 23 Apr 2024

  36. LLM Settings – Nextra. https://www.promptingguide.ai/introduction/settings. Accessed 23 Apr 2024

  37. Kugele, S., Franklin, S.: Learning in LIDA. Cogn. Syst. Res. 66, 176–200 (2021). https://doi.org/10.1016/j.cogsys.2020.11.001

    Article  Google Scholar 

  38. Agrawal, P., Franklin, S.: Multi-layer cortical learning algorithms. In: 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pp. 141–147 (2014). https://doi.org/10.1109/CCMB.2014.7020707

  39. Agrawal, P.: Applications of Sparse Representations. Electron. Theses Diss. (2019)

    Google Scholar 

  40. Kugele, S.C.: Embodied, Simulation-Based Cognition: A Hybrid Approach (2023)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. The Pennsylvania State University, The Behrend College, Erie, PA, 16563, USA

    Pulin Agrawal & Arpan Yagnik

  2. Memphis, TN, 38017, USA

    Daqi Dong

Authors
  1. Pulin Agrawal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arpan Yagnik
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daqi Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pulin Agrawal .

Editor information

Editors and Affiliations

  1. CADIA, Reykjavik University, Reykjavík, Iceland

    Kristinn R. Thórisson

  2. Temple University, Philadelphia, PA, USA

    Peter Isaev

  3. CADIA, Reykjavík University, Reykjavík, Iceland

    Arash Sheikhlar

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Agrawal, P., Yagnik, A., Dong, D. (2024). Generative AI Can Be Creative Too. In: Thórisson, K.R., Isaev, P., Sheikhlar, A. (eds) Artificial General Intelligence. AGI 2024. Lecture Notes in Computer Science(), vol 14951. Springer, Cham. https://doi.org/10.1007/978-3-031-65572-2_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-65572-2_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-65571-5

  • Online ISBN: 978-3-031-65572-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics