A Survey on Large Language Model Hallucination via a Creativity Perspective
It addresses the problem of balancing reliability and creativity in LLMs for researchers and practitioners, but it is incremental as it synthesizes existing literature without new empirical results.
This survey explores whether hallucinations in large language models (LLMs), typically viewed as limitations, could be leveraged as a source of creativity, reviewing their taxonomy, negative impacts, and potential benefits in fostering creative applications.
Hallucinations in large language models (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.