# SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

arXiv: https://arxiv.org/abs/2511.06446 · HTML: https://mlsanity.com/paper/2511.06446/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus](https://mlsanity.com/paper/2304.04358/) (2023)
- [FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG](https://mlsanity.com/paper/2410.10293/) (2024)
- [KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis](https://mlsanity.com/paper/2006.00088/) (2020)
- [KBLaM: Knowledge Base augmented Language Model](https://mlsanity.com/paper/2410.10450/) (2024)
- [Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese](https://mlsanity.com/paper/2407.01080/) (2024)
- [EvolKV: Evolutionary KV Cache Compression for LLM Inference](https://mlsanity.com/paper/2509.08315/) (2025)

## Built on by (most cited first, 2 of 2)

- [RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection](https://mlsanity.com/paper/2608.01630/) (2026)
- [PReM: Learning What to Preserve and When to Refresh for Context Compression](https://mlsanity.com/paper/2607.14327/) (2026)

## Abstract (arXiv)

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and injects them into LLMs' KV cache. Building on this representation, we employ a two-stage training paradigm: first locating a dedicated retrieval layer within the LLM, and then applying an attention-based loss at this layer to explicitly supervise attention toward relevant KB entries. Unlike traditional retrieval-augmented generation methods that rely heavily on the performance of external retrievers and multi-stage pipelines, SR-KI supports end-to-end inference by performing retrieval entirely within the models latent space. This design enables efficient compression of injected knowledge and facilitates dynamic knowledge updates. Comprehensive experiments demonstrate that SR-KI enables the integration of up to 40K KBs into a 7B LLM on a single A100 40GB GPU, and achieves strong retrieval performance, maintaining over 98% Recall@10 on the best-performing task and exceeding 88% on average across all tasks. Task performance on question answering and KB ID generation also demonstrates that SR-KI maintains strong performance while achieving up to 99.75% compression of the injected KBs.