arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09450cs.AIcs.CLcs.LGq-bio.NC
收藏

受人类启发的无限上下文LLM情景记忆

Human-inspired Episodic Memory for Infinite Context LLMs

Huawei Noah’s Ark Lab(华为诺亚实验室);University College London(伦敦大学学院)

Zafeirios Fountas, Martin A Benfeghoul, Adnan Oomerjee, Fenia Christopoulou, Gerasimos Lampouras, Haitham Bou-Ammar, Jun Wang

AI总结:

本文提出EM-LLM方法,将人类情景记忆和事件认知整合到LLMs中,无需微调即可处理无限上下文,通过贝叶斯惊奇度和图论边界细化组织事件,在多项基准测试中表现优于现有模型。

摘要:

大型语言模型(LLMs)展现出了卓越的能力,但在处理大量上下文时仍然面临困难,这限制了它们在长序列中保持连贯性和准确性的能力。相比之下,人类大脑擅长在跨越一生的巨大时间尺度上组织和检索情景经验。在这项工作中,我们引入了EM-LLM,这是一种新颖的方法,将人类情景记忆和事件认知的关键方面整合到LLMs中,无需微调,使它们能够处理实际上无限的上下文长度,同时保持计算效率。EM-LLM以在线方式结合贝叶斯惊奇度和图论边界细化,将标记序列组织成连贯的情景事件。在需要时,通过两阶段记忆过程检索这些事件,结合基于相似性和时间相邻性的检索,以实现对相关信息的高效、受人类启发的访问。在LongBench和$\infty$-Bench基准上的实验证明了EM-LLM的卓越性能,在各种基线LLMs上始终优于最先进的检索模型InfLLM。此外,EM-LLM在广泛的任务中优于其流行的对应物RAG,同时需要相似的资源。值得注意的是,EM-LLM的性能在大多数任务中甚至超过了全上下文模型,同时成功地在1000万个标记上执行检索——这对于此类模型来说在计算上是不可行的。最后,我们的分析揭示了EM-LLM的事件分割与人类感知事件之间的强相关性,表明该人工系统与其生物对应物之间存在相似性,从而为探索人类记忆机制提供了一个新颖的计算框架。

英文摘要:

Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy over long sequences. In contrast, the human brain excels at organising and retrieving episodic experiences across vast temporal scales, spanning a lifetime. In this work, we introduce EM-LLM, a novel approach that integrates key aspects of human episodic memory and event cognition into LLMs with no fine-tuning, enabling them to handle practically infinite context lengths while maintaining computational efficiency. EM-LLM organises sequences of tokens into coherent episodic events using a combination of Bayesian surprise and graph-theoretic boundary refinement in an online fashion. When needed, these events are retrieved through a two-stage memory process, combining similarity-based and temporally contiguous retrieval for efficient, human-inspired access to relevant information. Experiments on the LongBench and $\infty$-Bench benchmarks demonstrate EM-LLM's superior performance, consistently outperforming the state-of-the-art retrieval model InfLLM across various baseline LLMs. In addition, EM-LLM outperforms its popular counterpart, RAG, in a wide range of tasks, while requiring similar resources. Notably, EM-LLM's performance even surpasses full-context models in most tasks, while successfully performing retrieval across 10 million tokens -- a scale computationally infeasible for such models. Finally, our analysis reveals strong correlations between EM-LLM's event segmentation and human-perceived events, suggesting parallels between this artificial system and its biological counterpart, thereby offering a novel computational framework for exploring human memory mechanisms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑