Aspects of human memory and Large Language Models
This research addresses the problem of understanding memory mechanisms in AI for cognitive science and AI researchers, but it is incremental as it builds on existing LLM studies without introducing new methods.
The study investigated memory properties in Large Language Models (LLMs) and found surprising similarities with key characteristics of human memory, suggesting these human-like features are learned from training data statistics rather than inherent to the LLM architecture.
Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but are rather learned from the statistics of the training textual data. These results strongly suggest that the biological features of human memory leave an imprint on the way that we structure our textual narratives.