SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

arXiv:2606.15971 · cs.CL · Submitted 2026-06-14 · Read on arXiv

cs.CL

Submitted: 2026-06-14

Updated: 2026-08-25

Comments: v2: revised version, with the earlier copy of this revision inadvertently posted as a separate submission (arXiv:2608.12129, now withdrawn)

Code: https://github.com/Zleap-AI/SAG-Benchmark

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 16× in this paper · explained in 3 episodes
• Knowledge Graph — 15× in this paper · explained in 7 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation — 9× in this paper
• Hypergraph — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Core — 7× in this paper · explained in 2 episodes
• Pruning — 7× in this paper · explained in 4 episodes
• Multi-hop Reasoning — 6× in this paper · explained in 3 episodes
• Knowledge graphs — 5× in this paper · explained in 2 episodes
• Agent Memory — 4× in this paper · explained in 1 episode
• Empirical Methods in Natural Language Processing — 4× in this paper
• Retrieval-Augmented Generation (RAG) — 4× in this paper · explained in 16 episodes
• Decoupling — 3× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• Text-to-SQL — 3× in this paper · explained in 3 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• SQL-Retrieval Augmented Generation — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• International Conference on Machine Learning — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Message Passing for Hyper-Relational Knowledge Graphs
• LightRAG: Simple and Fast Retrieval-Augmented Generation
• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
• ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
• Retrieval-Augmented Generation with Hierarchical Knowledge
• StructGPT: A General Framework for Large Language Model to Reason over Structured Data
• NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
• StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
• TAPEX: Table Pre-training via Learning a Neural SQL Executor
• Multi-hop Question Answering
• BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
• Qwen3 Technical Report
• RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
• Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
• Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering
• Knowledge Graph Prompting for Multi-Document Question Answering
• C-Pack: Packed Resources For General Chinese Embeddings

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