# KBLaM: Knowledge Base augmented Language Model

arXiv: https://arxiv.org/abs/2410.10450 · HTML: https://mlsanity.com/paper/2410.10450/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 49 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [Learning Video Representations from Large Language Models](https://mlsanity.com/paper/2212.04501/) (2022)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Long-Context Language Modeling with Parallel Context Encoding](https://mlsanity.com/paper/2402.16617/) (2024)
- [Improving Neural Language Models with a Continuous Cache](https://mlsanity.com/paper/1612.04426/) (2016)
- [Parallel Context Windows for Large Language Models](https://mlsanity.com/paper/2212.10947/) (2022)
- [Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?](https://mlsanity.com/paper/2406.13121/) (2024)

## Built on by (most cited first, 16 of 16)

- [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025)
- [LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2507.05346/) (2025)
- [KV-Skill: Forging Expertise in the Model's Native Language](https://mlsanity.com/paper/2608.05475/) (2026)
- [SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention](https://mlsanity.com/paper/2511.06446/) (2025)
- [Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning](https://mlsanity.com/paper/2605.05632/) (2026)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.12668/) (2025)
- [AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM](https://mlsanity.com/paper/2510.17934/) (2025)
- [RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection](https://mlsanity.com/paper/2608.01630/) (2026)
- [Automating Violence Detection and Categorization from Ancient Texts](https://mlsanity.com/paper/2503.08192/) (2025)
- [Accelerating Language Model Workflows with Prompt Choreography](https://mlsanity.com/paper/2512.23049/) (2025)
- [Scalable Model-Based Clustering with Sequential Monte Carlo](https://mlsanity.com/paper/2604.14810/) (2026)
- [KARLA: Knowledge-base Augmented Retrieval for Language Models](https://mlsanity.com/paper/2606.26807/) (2026)
- [KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models](https://mlsanity.com/paper/2606.30258/) (2026)
- [Co-LMLM: Continuous-Query Limited Memory Language Models](https://mlsanity.com/paper/2607.07707/) (2026)
- [TokenMem: Faithful Knowledge Injection for Frozen LLMs](https://mlsanity.com/paper/2607.22625/) (2026)

## Abstract (arXiv)

In this paper, we propose Knowledge Base augmented Language Model (KBLaM), a new method for augmenting Large Language Models (LLMs) with external knowledge. KBLaM works with a knowledge base (KB) constructed from a corpus of documents, transforming each piece of knowledge in the KB into continuous key-value vector pairs via pre-trained sentence encoders with linear adapters and integrating them into pre-trained LLMs via a specialized rectangular attention mechanism. Unlike Retrieval-Augmented Generation, KBLaM eliminates external retrieval modules, and unlike in-context learning, its computational overhead scales linearly with KB size rather than quadratically. Our approach enables integrating a large KB of more than 10K triples into an 8B pre-trained LLM of only 8K context window on one single A100 80GB GPU and allows for dynamic updates without model fine-tuning or retraining. Experiments demonstrate KBLaM's effectiveness in various tasks, including question-answering and open-ended reasoning, while providing interpretable insights into its use of the augmented knowledge. Code and datasets are available at https://github.com/microsoft/KBLaM/