A Survey on Large Language Model Hallucination via a Creativity Perspective

2024/02/02 by Xuhui Jiang, Yuxing Tian, Jiang, Xuhui +9 · 18 citations
Computer Science · Social Sciences · #Advanced Computing and Algorithms #Artificial Intelligence (cs.AI) #Data Visualization and Analytics #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Online Learning and Analytics

paper · pdf · doi:10.48550/arxiv.2402.06647

openalex publication_date 2024/02/02 · openalex created_date 2024/02/14 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• How Well Can AI Generate Backlogs from App Mockups?
• From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
• A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI
• Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
• FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
• Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning
• Large Language Models Hallucination: A Comprehensive Survey
• Library Hallucinations in LLMs: Risk Analysis Grounded in Developer Queries
• Are Hallucinations Bad Estimations?
• MazeMate: An LLM-Powered Chatbot to Support Computational Thinking in Gamified Programming Learning
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers
• Conservative Bias in Large Language Models: Measuring Relation Predictions
• Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
• Are Reasoning Models More Prone to Hallucination?
• From Editorial Records to Structured Provenance Information: Documenting Warrant in Knowledge Organization Systems Using Large Language Models
• MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
• Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
• DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

Related

• Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers
• Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs
• An Audit on the Perspectives and Challenges of Hallucinations in NLP
• From "Hallucination" to "Suture": Insights from Language Philosophy to Enhance Large Language Models
• 🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models