RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
Shicheng Xu, Liang Pang, Liyi Chen, Zihao Wei, Jingcheng Deng, Yan Gao, Yi Wu, Yao Hu, Huawei Shen, Xueqi Cheng
cs.CL, cs.AI
Submitted: 2026-08-03
Comments: 16 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
- Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval
- SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
- Mass-Editing Memory in a Transformer
- LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks
- Toward Understanding Catastrophic Forgetting in Continual Learning
- Retrieval-Augmented Generation for Large Language Models: A Survey
- AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
- Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
- Gemini Embedding: Generalizable Embeddings from Gemini
- With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation
- Group Sequence Policy Optimization
- MLP Memory: A Retriever-Pretrained Memory for Large Language Models
- Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
- A Comprehensive Study of Knowledge Editing for Large Language Models
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering