Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Survey on Large Language Model Hallucination via a Creativity Perspective (2402.06647v1)

Published 2 Feb 2024 in cs.AI and cs.HC

Abstract: Hallucinations in LLMs are always seen as limitations. However, could they also be a source of creativity? This survey explores this possibility, suggesting that hallucinations may contribute to LLM application by fostering creativity. This survey begins with a review of the taxonomy of hallucinations and their negative impact on LLM reliability in critical applications. Then, through historical examples and recent relevant theories, the survey explores the potential creative benefits of hallucinations in LLMs. To elucidate the value and evaluation criteria of this connection, we delve into the definitions and assessment methods of creativity. Following the framework of divergent and convergent thinking phases, the survey systematically reviews the literature on transforming and harnessing hallucinations for creativity in LLMs. Finally, the survey discusses future research directions, emphasizing the need to further explore and refine the application of hallucinations in creative processes within LLMs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Can knowledge graphs reduce hallucinations in llms?: A survey. ArXiv preprint, 2023.
  2. T. M. Amabile. Social psychology of creativity: A consensual assessment technique. Journal of Personality and Social Psychology, 1982.
  3. John Baer. The importance of domain-specific expertise in creativity. Roeper Review, 2015.
  4. A first look at the role of domain-general cognitive and creative abilities in jazz improvisation. Psychomusicology: Music, Mind, & Brain, 2013.
  5. Roger E Beaty. The neuroscience of musical improvisation. Neuroscience & Biobehavioral Reviews, 51:108–117, 2015.
  6. To create or to recall? neural mechanisms underlying the generation of creative new ideas. NeuroImage, 2014.
  7. Chateval: Towards better llm-based evaluators through multi-agent debate. ArXiv preprint, 2023.
  8. Hierarchical reinforcement learning as creative problem solving. Robotics and Autonomous Systems, 2016.
  9. (un)structured creativity in information systems organizations. MIS Q., 1993.
  10. David Cropley. Is artificial intelligence more creative than humans? : Chatgpt and the divergent association task. Learning Letters, 2023.
  11. Neural path hunter: Reducing hallucination in dialogue systems via path grounding. In Proc. of EMNLP, 2021.
  12. Howard Gardner. Creating minds: An anatomy of creativity seen through the lives of Freud, Einstein, Picasso, Stravinsky, Eliot, Graham, and Ghandi. Civitas books, 2011.
  13. Associative processing and paranormal belief. Psychiatry and Clinical Neurosciences, 2001.
  14. Pushing gpt’s creativity to its limits: Alternative uses and torrance tests. 2023.
  15. Joy Peter Guilford. Creativity: A quarter century of progress. In Perspectives in creativity, pages 37–59. Routledge, 2017.
  16. The originality of machines: Ai takes the torrance test. Journal of Creativity, 2023.
  17. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ArXiv preprint, 2023.
  18. Artificial intelligence is more creative than humans: A cognitive science perspective on the current state of generative language models. 2023.
  19. Survey of hallucination in natural language generation. ACM Computing Surveys, 2023.
  20. Beyond big and little: The four c model of creativity. Review of General Psychology, 2009.
  21. Thinking creatively with sounds and words: Normstechnical manual. Res. ed.) Bensenville, IL: Scholastic Testing Service, 1973.
  22. Best humans still outperform artificial intelligence in a creative divergent thinking task. Scientific reports, 2023.
  23. Minhyeok Lee. A mathematical investigation of hallucination and creativity in gpt models. Mathematics, 2023.
  24. Halueval: A large-scale hallucination evaluation benchmark for large language models. In Proc. of EMNLP, 2023.
  25. Encouraging divergent thinking in large language models through multi-agent debate. ArXiv preprint, 2023.
  26. TruthfulQA: Measuring how models mimic human falsehoods. In Proc. of ACL, 2022.
  27. Remote associates test: An empirical proof of concept. Behavior Research Methods, 2018.
  28. Sarnoff A. Mednick. The associative basis of the creative process. Psychological review, 1962.
  29. Large language models are fixated by red herrings: Exploring creative problem solving and einstellung effect using the only connect wall dataset, 2023.
  30. Cultural influences on artistic creativity and its evaluation. International Journal of Psychology, 2001.
  31. Naming unrelated words predicts creativity. Proceedings of the National Academy of Sciences, 2021.
  32. Jeff Pressing. Psychological constraints on improvisational expertise and communication. In the course of performance: Studies in the world of musical improvisation, 1998.
  33. Jeff Pressing. Improvisation: Methods and models. In Physical Theatres: A Critical Reader, pages 66–78. Routledge, 2007.
  34. A survey of hallucination in large foundation models. ArXiv preprint, 2023.
  35. Supermind ideator: Exploring generative ai to support creative problem-solving. ArXiv preprint, 2023.
  36. Salesforce. A world without ai is becoming unthinkable, 2023.
  37. Hallucination mitigation in natural language generation from large-scale open-domain knowledge graphs. In Proc. of EMNLP, 2023.
  38. Assessing creativity with divergent thinking tasks: exploring the reliability and validity of new subjective scoring methods. Psychology of Aesthetics, Creativity, and the Arts, 2008.
  39. Putting gpt-3’s creativity to the alternative uses test, 2022.
  40. Brainstorm, then select: a generative language model improves its creativity score. In The AAAI-23 Workshop on Creative AI Across Modalities, 2023.
  41. Think-on-graph: Deep and responsible reasoning of large language model with knowledge graph. arXiv preprint arXiv:2307.07697, 2023.
  42. Macgyver: Are large language models creative problem solvers? ArXiv preprint, 2023.
  43. A comprehensive survey of hallucination mitigation techniques in large language models. ArXiv preprint, 2024.
  44. E Paul Torrance. Creativity in the classroom; what research says to the teacher. 1977.
  45. Llama: Open and efficient foundation language models. ArXiv preprint, 2023.
  46. Donald J. Treffinger. Creativity, creative thinking, and critical thinking: In search of definitions. Gifted and Talented International, 1998.
  47. Med-halt: Medical domain hallucination test for large language models. ArXiv preprint, 2023.
  48. Can ai be as creative as humans?, 2024.
  49. Feng Wang. Lighthouse: A survey of agi hallucination. ArXiv preprint, 2024.
  50. Is a fool with a (n ai) tool still a fool? an empirical study of the creative quality of human–ai collaboration. ACIS 2023 Proceedings, 2023.
  51. Cognitive mirage: A review of hallucinations in large language models. ArXiv preprint, 2023.
  52. Creative agents: Empowering agents with imagination for creative tasks. ArXiv preprint, 2023.
  53. Siren’s song in the ai ocean: A survey on hallucination in large language models. ArXiv preprint, 2023.
  54. Chen Zhang. User-controlled knowledge fusion in large language models: Balancing creativity and hallucination. ArXiv preprint, 2023.
  55. Assessing and understanding creativity in large language models. ArXiv preprint, 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Xuhui Jiang (16 papers)
  2. Yuxing Tian (6 papers)
  3. Fengrui Hua (5 papers)
  4. Chengjin Xu (36 papers)
  5. Yuanzhuo Wang (16 papers)
  6. Jian Guo (76 papers)
Citations (12)