# Self-Updatable Large Language Models by Integrating Context into Model Parameters

arXiv: https://arxiv.org/abs/2410.00487 · HTML: https://mlsanity.com/paper/2410.00487/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 52 references that are in the map.
- First posted on arXiv 1 Oct 2024.

## Builds on (most cited first, 30 of 46)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Llemma: An Open Language Model For Mathematics](https://mlsanity.com/paper/2310.10631/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [ERNIE 2.0: A Continual Pre-training Framework for Language Understanding](https://mlsanity.com/paper/1907.12412/) (2019)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [Transformer-Patcher: One Mistake worth One Neuron](https://mlsanity.com/paper/2301.09785/) (2023)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Towards Continual Knowledge Learning of Language Models](https://mlsanity.com/paper/2110.03215/) (2021)
- [LAMOL: LAnguage MOdeling for Lifelong Language Learning](https://mlsanity.com/paper/1909.03329/) (2019)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)
- [Focused Transformer: Contrastive Training for Context Scaling](https://mlsanity.com/paper/2307.03170/) (2023)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)

## Built on by (most cited first, 21 of 21)

- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Mem-α: Learning Memory Construction via Reinforcement Learning](https://mlsanity.com/paper/2509.25911/) (2025)
- [Skill-R1: Agent Skill Evolution via Reinforcement Learning](https://mlsanity.com/paper/2605.09359/) (2026)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning](https://mlsanity.com/paper/2602.18493/) (2026)
- [Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection](https://mlsanity.com/paper/2505.12306/) (2025)
- [Memorization and Knowledge Injection in Gated LLMs](https://mlsanity.com/paper/2504.21239/) (2025)
- [Mem-W: Latent Memory-Native GUI Agents](https://mlsanity.com/paper/2605.09317/) (2026)
- [Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering](https://mlsanity.com/paper/2606.29824/) (2026)
- [OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents](https://mlsanity.com/paper/2605.11169/) (2026)
- [Simulating Human Memory with Language Models](https://mlsanity.com/paper/2605.25680/) (2026)
- [Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.12668/) (2025)
- [Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck](https://mlsanity.com/paper/2605.08526/) (2026)
- [SaliMory: Orchestrating Cognitive Memory for Conversational Agents](https://mlsanity.com/paper/2606.04120/) (2026)
- [EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts](https://mlsanity.com/paper/2606.05513/) (2026)
- [RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents](https://mlsanity.com/paper/2609.23466/) (2026)
- [MemDLM: Memory-Enhanced DLM Training](https://mlsanity.com/paper/2603.22241/) (2026)
- [SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation](https://mlsanity.com/paper/2605.20189/) (2026)
- [MemTools: A Unified Research Framework for Interoperable Agent Memory](https://mlsanity.com/paper/2607.21404/) (2026)
- [Continual Learning in Transition](https://mlsanity.com/paper/2608.06216/) (2026)

## Abstract (arXiv)

Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge. Two critical factors in assimilating these experiences are (1) Efficacy: the ability to accurately remember recent events; (2) Retention: the capacity to recall long-past experiences. Current methods either embed experiences within model parameters using continual learning, model editing, or knowledge distillation techniques, which often struggle with rapid updates and complex interactions, or rely on external storage to achieve long-term retention, thereby increasing storage requirements. In this paper, we propose SELF-PARAM (Self-Updatable Large Language Models with Parameter Integration). SELF-PARAM requires no extra parameters while ensuring near-optimal efficacy and long-term retention. Our method employs a training objective that minimizes the Kullback-Leibler (KL) divergence between the predictions of an original model (with access to contextual information) and a target model (without such access). By generating diverse question-answer pairs related to the knowledge and minimizing the KL divergence across this dataset, we update the target model to internalize the knowledge seamlessly within its parameters. Evaluations on question-answering and conversational recommendation tasks demonstrate that SELF-PARAM significantly outperforms existing methods, even when accounting for non-zero storage requirements. This advancement paves the way for more efficient and scalable integration of experiences in large language models by embedding knowledge directly into model parameters.