Redefining "Hallucination" in LLMs: Towards a psychology-informed framework for mitigating misinformation
This work addresses the issue of LLM-generated misinformation for users and developers, offering an incremental framework to refine understanding and solutions.
The paper tackles the problem of misinformation from LLM hallucinations by questioning the term's appropriateness and proposing a psychology-informed taxonomy based on cognitive biases, aiming to develop targeted mitigation strategies for improved reliability.
In recent years, large language models (LLMs) have become incredibly popular, with ChatGPT for example being used by over a billion users. While these models exhibit remarkable language understanding and logical prowess, a notable challenge surfaces in the form of "hallucinations." This phenomenon results in LLMs outputting misinformation in a confident manner, which can lead to devastating consequences with such a large user base. However, we question the appropriateness of the term "hallucination" in LLMs, proposing a psychological taxonomy based on cognitive biases and other psychological phenomena. Our approach offers a more fine-grained understanding of this phenomenon, allowing for targeted solutions. By leveraging insights from how humans internally resolve similar challenges, we aim to develop strategies to mitigate LLM hallucinations. This interdisciplinary approach seeks to move beyond conventional terminology, providing a nuanced understanding and actionable pathways for improvement in LLM reliability.