SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
This addresses the limitation of LLMs in processing lengthy inputs for tasks like long-term dialogues, book summarization, and meeting summarization, though it appears incremental as it builds on existing memory and retrieval concepts.
The paper tackles the problem of large language models losing critical historical information due to limited input length by proposing the Self-Controlled Memory (SCM) framework, which enhances long-term memory and recall, achieving better retrieval recall and more informative responses in long-term dialogues compared to baselines.
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information. Our SCM framework comprises three key components: an LLM-based agent serving as the backbone of the framework, a memory stream storing agent memories, and a memory controller updating memories and determining when and how to utilize memories from memory stream. Additionally, the proposed SCM is able to process ultra-long texts without any modification or fine-tuning, which can integrate with any instruction following LLMs in a plug-and-play paradigm. Furthermore, we annotate a dataset to evaluate the effectiveness of SCM for handling lengthy inputs. The annotated dataset covers three tasks: long-term dialogues, book summarization, and meeting summarization. Experimental results demonstrate that our method achieves better retrieval recall and generates more informative responses compared to competitive baselines in long-term dialogues. (https://github.com/wbbeyourself/SCM4LLMs)