HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- URL: http://arxiv.org/abs/2405.14831v3
- Date: Tue, 14 Jan 2025 16:17:49 GMT
- Title: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- Authors: Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su,
- Abstract summary: We introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory.
We show that our method outperforms the state-of-the-art methods remarkably, by up to 20%.
Our method can tackle new types of scenarios that are out of reach of existing methods.
- Score: 24.529215038221956
- License:
- Abstract: In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressive accomplishments, large language models (LLMs), even with retrieval-augmented generation (RAG), still struggle to efficiently and effectively integrate a large amount of new experiences after pre-training. In this work, we introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory to enable deeper and more efficient knowledge integration over new experiences. HippoRAG synergistically orchestrates LLMs, knowledge graphs, and the Personalized PageRank algorithm to mimic the different roles of neocortex and hippocampus in human memory. We compare HippoRAG with existing RAG methods on multi-hop question answering and show that our method outperforms the state-of-the-art methods remarkably, by up to 20%. Single-step retrieval with HippoRAG achieves comparable or better performance than iterative retrieval like IRCoT while being 10-30 times cheaper and 6-13 times faster, and integrating HippoRAG into IRCoT brings further substantial gains. Finally, we show that our method can tackle new types of scenarios that are out of reach of existing methods. Code and data are available at https://github.com/OSU-NLP-Group/HippoRAG.
Related papers
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models [6.380729797938521]
retrieval-augmented generation (RAG) has become the dominant way to introduce new information.
Recent RAG approaches augment vector embeddings with various structures like knowledge graphs to address some gaps, namely sense-making and associativity.
We propose HippoRAG 2, a framework that outperforms standard RAG comprehensively on factual, sense-making, and associative memory tasks.
arXiv Detail & Related papers (2025-02-20T18:26:02Z) - P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task [94.08478298711789]
Embodied Everyday Task is a popular task in the embodied AI community.
Natural language instructions often lack explicit task planning.
Extensive training is required to equip models with knowledge of the task environment.
arXiv Detail & Related papers (2024-09-17T15:29:34Z) - RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation [54.707460684650584]
Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention.
Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG)
RAGLAB is a modular and research-oriented open-source library that reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms.
arXiv Detail & Related papers (2024-08-21T07:20:48Z) - Human-like Episodic Memory for Infinite Context LLMs [13.211261438927798]
Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts.
In this work, we introduce EM-LLM, a novel approach that integrates key aspects of human episodic memory and event cognition into LLMs.
EM-LLM organises sequences of tokens into coherent episodic events using a combination of Bayesian surprise and graph-theoretic boundary refinement.
arXiv Detail & Related papers (2024-07-12T17:34:03Z) - ReconBoost: Boosting Can Achieve Modality Reconcilement [89.4377895465204]
We study the modality-alternating learning paradigm to achieve reconcilement.
We propose a new method called ReconBoost to update a fixed modality each time.
We show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others.
arXiv Detail & Related papers (2024-05-15T13:22:39Z) - Recursively Summarizing Enables Long-Term Dialogue Memory in Large
Language Models [75.98775135321355]
Given a long conversation, large language models (LLMs) fail to recall past information and tend to generate inconsistent responses.
We propose to generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability.
arXiv Detail & Related papers (2023-08-29T04:59:53Z) - Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo)
Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
arXiv Detail & Related papers (2022-10-23T23:49:08Z) - Representation Memorization for Fast Learning New Knowledge without
Forgetting [36.55736909586313]
The ability to quickly learn new knowledge is a big step towards human-level intelligence.
We consider scenarios that require learning new classes or data distributions quickly and incrementally over time.
We propose "Memory-based Hebbian Adaptation" to tackle the two major challenges.
arXiv Detail & Related papers (2021-08-28T07:54:53Z) - Predictive Coding Can Do Exact Backpropagation on Any Neural Network [40.51949948934705]
We generalize (IL and) Z-IL by directly defining them on computational graphs.
This is the first biologically plausible algorithm that is shown to be equivalent to BP in the way of updating parameters on any neural network.
arXiv Detail & Related papers (2021-03-08T11:52:51Z) - One-shot learning for the long term: consolidation with an artificial
hippocampal algorithm [0.0]
We claim that few-shot learning should be long term, assimilating knowledge for the future, without forgetting previous concepts.
We tested whether an artificial hippocampal algorithm, AHA, could be used with a conventional ML model analogous to the neocortex.
Results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting.
arXiv Detail & Related papers (2021-02-15T12:07:26Z) - Continual Learning for Natural Language Generation in Task-oriented
Dialog Systems [72.92029584113676]
Natural language generation (NLG) is an essential component of task-oriented dialog systems.
We study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally.
The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before.
arXiv Detail & Related papers (2020-10-02T10:32:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.