OpenIntelligenceResearch notes · 13 papers
Research Notes
Papers and references I had found while working through OpenIntelligence. Most of this started as curiosity around how far an Apple Intelligence-capable device could go as a local document intelligence system. These are most of the papers that shaped the RAG engine.
RAG Engine Papers
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
The original RAG paper I used as the baseline idea: retrieve evidence, then generate against it.
Retrieval-Augmented Generation for Large Language Models: A Survey
The map for the main RAG pieces: retrieval, generation, augmentation, routing, and evaluation.
Retrieval-Augmented Generation for AI-Generated Content: A Survey
General background on how retrieval changes answer generation and grounding.
Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods
The ranking paper behind fusing keyword and vector results without pretending one signal always wins.
vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents
A useful reference for local-first hybrid retrieval, FTS/vector fusion, and ranking diagnostics.
RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal RAG on the Edge
A reference point for keeping retrieval local, embeddable, and small enough for edge-style constraints.
Lost in the Middle: How Language Models Use Long Contexts
The paper that pushed me to care about where retrieved chunks land inside a tight context window.
Precise Zero-Shot Dense Retrieval without Relevance Labels
The HyDE paper behind generating a better search target before retrieving against the real corpus.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Useful for the retrieval-needed and self-checking ideas around grounded answers.
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Background for trying multiple retrieved evidence paths and then verifying the better answer.
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Background reading for recursive retrieval, planning, and agent-style query execution.
Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
A checklist source for relevance, source quality, confidence, and weak-retrieval warnings.
Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
Helpful for sanity-checking tradeoffs around retrieval quality, grounding, efficiency, and robustness.