LightHouse: A Survey of AGI Hallucination
This is an incremental survey paper that aims to help researchers by consolidating knowledge on AGI hallucinations, a bottleneck in AI development.
The paper addresses the problem of hallucinations in artificial general intelligence (AGI), particularly in multimodal systems, by providing a survey that summarizes current research and suggests future directions, with no concrete results or numbers reported.
With the development of artificial intelligence, large-scale models have become increasingly intelligent. However, numerous studies indicate that hallucinations within these large models are a bottleneck hindering the development of AI research. In the pursuit of achieving strong artificial intelligence, a significant volume of research effort is being invested in the AGI (Artificial General Intelligence) hallucination research. Previous explorations have been conducted in researching hallucinations within LLMs (Large Language Models). As for multimodal AGI, research on hallucinations is still in an early stage. To further the progress of research in the domain of hallucinatory phenomena, we present a bird's eye view of hallucinations in AGI, summarizing the current work on AGI hallucinations and proposing some directions for future research.