Knowledge Tree
Relations (1)
related 0.20 — supporting 2 facts
Large Language Models and working memory are connected through research directly integrating the two concepts, as evidenced by [1] on 'Large language models with controllable working memory' and [2] examining 'Working memory identifies reasoning limits in language models' specifically in LLMs.
Facts (2)
Sources
A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org 2 facts
referenceDaliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix Yu, and Sanjiv Kumar authored 'Large language models with controllable working memory', published in the Findings of the Association for Computational Linguistics: ACL 2023.
referenceZhang et al. (2024a) published 'Working memory identifies reasoning limits in language models' in the Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, which examines the relationship between working memory and reasoning capabilities in LLMs.