Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
cs.CL, cs.AI, cs.LG
Submitted: 2026-06-03
Updated: 2026-10-28
Comments: 9 pages, 4 figures, plus supplementary appendix
License: http://creativecommons.org/licenses/by/4.0/
The gist: Real-world data spans tables, documents, and semi-structured files with implicit semantics.
Terminology
Abstract
Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identity keys, foreign keys, and source hierarchy; and the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph. At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations. In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.
Sources
- Hybrid Graphs for Table-and-Text based Question Answering using LLMs
- Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Retrieval-Augmented Generation for Large Language Models: A Survey
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- Dense Passage Retrieval for Open-Domain Question Answering
- The Dawn of Natural Language to SQL: Are We Fully Ready?
- Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
- HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
- MSRS: Evaluating Multi-Source Retrieval-Augmented Generation
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
- CRAG -- Comprehensive RAG Benchmark
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data