Larimar: Large Language Models with Episodic Memory Control
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, one-shot updates of knowledge without the need for computationally expensive re-training or fine-tuning. Experimental results on multiple fact editing benchmarks demonstrate that Larimar attains accuracy comparable to most competitive baselines, even in the challenging sequential editing setup, but also excels in speed - yielding speed-ups of 8-10x depending on the base LLM - as well as flexibility due to the proposed architecture being simple, LLM-agnostic, and hence general. We further provide mechanisms for selective fact forgetting, information leakage prevention, and input context length generalization with Larimar and show their effectiveness. Our code is available at https://github.com/IBM/larimar
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Needle in the Haystack for Memory Based Large Language Models
Current large language models (LLMs) often perform poorly on simple fact retrieval tasks. Here we investigate if coupling a dynamically adaptable external memory to a LLM can alleviate this problem. For this purpose, we …
DecoderGPULanguage ModelingLanguage Modelling+1Solving Continuous Control with Episodic Memory
Episodic memory lets reinforcement learning algorithms remember and exploit promising experience from the past to improve agent performance. Previous works on memory mechanisms show benefits of using episodic-based data …
continuous-controlContinuous ControlOpenAI GymReinforcement Learning (RL)Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory. We propose a new model-based episodic memory of trajectories addressing current limitations of e…
modelreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential memory improves sample and memory efficiency in Episodic Control
State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspire…
Deep Reinforcement LearningHippocampusreinforcement-learningReinforcement Learning+1Is prioritized sweeping the better episodic control?
Episodic control has been proposed as a third approach to reinforcement learning, besides model-free and model-based control, by analogy with the three types of human memory. i.e. episodic, procedural and semantic memory…
Reinforcement Learning