Retrieval, RAG & Evidence Grounding
32 reading notes
Explore engineering trade-offs in multimodal retrieval, GraphRAG, ranking, evidence discovery, and traceable answers.
Reader question
How can a system keep finding verifiable evidence as its corpus and tool surface grow?
Reading library
Read this topic in depth
Every paper reading currently filed under this research topic.
-
RetrievalRouter Reading: Choosing a Retrieval Route for Each Query
Intermediate Retrieval, memory, and production RAGRetrievalRouter routes each query among BM25, text-vector, multimodal, and reranking pipelines. This reading explains its soft-target policy, accuracy-latency results across 11 datasets, and the deployment costs and generalization questions its offline benchmark leaves open.
Understand it in 90 seconds
-
Librarian Agents: Preparing Reusable Workspaces Before Questions Arrive
Intermediate Retrieval, memory, and production RAGLibrarian Agents moves part of document retrieval before query time: a reinforcement-trained builder creates a navigable, provenance-linked filesystem for a separate answerer. This reading examines the 50 held-out BrowseComp-Plus corpus tasks, a distinct 443-question synthetic reuse set, BRIGHT transfer, token trade-offs, and the claims the evidence does not yet establish.
Understand it in 90 seconds
-
TRACE: Accountable Source Discovery in Digital Archives
Advanced Retrieval, memory, and production RAGTRACE turns retrieval over OCR-degraded French archives into an inspectable agent workflow: corpus-targeted decomposition, fused search, deferred relevance decisions, and cross-question reranking. Read its results on 1,752 questions alongside the limits of the public data version, internal deployment claims, and cost estimate.
Understand it in 90 seconds
-
EconSkills: How Web-Agent Skills Transfer and Get Retrieved
Advanced Agent runtime, safety, and evaluationEconSkills turns successful economic-data browsing traces into parameterized SOPs with scope, verification, and recovery steps. A known match transfers; library-scale retrieval remains constrained by coverage and approximate mismatches.
Understand it in 90 seconds
-
Stale-Document Poisoning: How RAG Can Recognize Evidence That No Longer Applies
Advanced Retrieval, memory, and production RAGAuthentic, once-correct documents can make RAG overturn an answer the model already got right. This reading examines 317 cross-domain knowledge reversals, the difference between dates and validity intervals, causal interventions, and a reranker whose gains depend on trustworthy metadata.
Understand it in 90 seconds
-
When Is Complex Chunking Worth It? Reading a Multi-Objective Chunking Evaluation
Intermediate Retrieval, memory, and production RAGA close reading of arXiv 2608.16586 v1: how eight chunking strategies change retrieval quality, indexing throughput, query speed, and memory—and where this benchmark stops.
Understand it in 90 seconds
-
The Source Link Is Intact, but the Rule Is Stale: How Agents Miss Updates Under a Verification Budget
Advanced Agent runtime, safety, and evaluationA deep reading of When Stale Constraints Go Unchecked: immutable provenance, append-only supersession, and stale-consistent decisions under a two-record verification budget. Audits four runs, the held-out correction, denominators, and the Zenodo artifact while bounding the synthetic evidence.
Understand it in 90 seconds
-
Does a Correct RAG Answer Mean the System Behaved Correctly? Reading The RAT
Advanced Retrieval, memory, and production RAGA deep read of The RAT: how a joint Bayesian model separates retrieval, abstention, and answer correctness, and what its annotation-budget results, judge calibration, partial retrieval analysis, and controlled Wikipedia scope do and do not establish.
Understand it in 90 seconds
-
BioPhys-Bridge: Making Scientific RAG Walk from Evidence to Physics, Mechanism, and Decision
Advanced Retrieval, memory, and production RAGA deep reading of BioPhys-Bridge (arXiv:2609.19180 v1): a benchmark that makes evidence IDs, values and units, physical equations, assumptions, biological mechanisms, and next decisions explicit, while separating attribution from scientific correctness.
Understand it in 90 seconds
-
RAFT: Making Troubleshooting RAG Retrieve the State That Led to a Fix
Advanced Retrieval, memory, and production RAGA deep reading of RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents (arXiv:2609.20754): closed support cases become state-transition trajectories, intermediate entries are retrieved, and the parent case is returned with its matched anchor.
Understand it in 90 seconds
-
Learning When to Trust: Measuring and Training Selective Trust with Selective Context Preference Optimization
Advanced Retrieval, memory, and production RAGA deep read of Learning When to Trust via Selective Context Preference Optimization: MIST holds each reasoning item fixed while varying clean, misleading, correct-context, and irrelevant-context signals; SC2W isolates clean-correct flips, and SCOPE reduces them with balanced DPO preference quartets while retaining the paper's text-only, contamination, and deployment-prevalence boundaries.
Understand it in 90 seconds
-
HyPE: Moving the RAG Question–Document Gap into Indexing
Intermediate Retrieval, memory, and production RAGA deep reading of Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings. HyPE precomputes hypothetical questions for every chunk and turns query-to-document retrieval into question-to-question matching, with strong six-dataset results but real indexing, freshness, chunking, and single-generator boundaries.
Understand it in 90 seconds
-
Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation
Advanced Retrieval, memory, and production RAGA deep reading of Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation: turning intermediate answer quality, utility, and trajectory signals into an early-stopping controller, then checking the savings and transfer boundary.
Understand it in 90 seconds
-
RAGSieve: Detecting RAG Knowledge-Poisoning Promotion with Self-Referenced Local Contrast
Advanced Retrieval, memory, and production RAGA deep read of RAGSieve: query-local and corpus-local references expose suspicious retrieval promotion without a trusted clean corpus, while the paper's boundary remains essential—promotion detection is not truth verification.
Understand it in 90 seconds
-
When Failure Propagates, Can We Still Find the Start? Causal Failure Attribution in Agentic RAG
Advanced Retrieval, memory, and production RAGA deep reading of When Failures Propagate: an interventional benchmark, three-hop MuSiQue, and certified content corruption that separate failure detection, causal attribution, propagation, and recovery in agentic RAG.
Understand it in 90 seconds
-
REVA: Moving RAG compression into reusable evidence views instead of paying per request
Advanced Retrieval, memory, and production RAGA critical reading of Nguyen et al.'s REVA (arXiv 2609.11209 v1): historical generator attention becomes a document-keyed score store, separating offline scoring from online rendering while exposing unseen-document fallback, local/global budgets, quality, and latency boundaries.
Understand it in 90 seconds
-
VikingRAG: Fewer Retrieval Rounds, Less Context Waste for Structured-Document RAG
Advanced Retrieval, memory, and production RAGA deep reading of VikingRAG: hierarchy-preserving URI-addressable storage, Search/List/Grep/Read tools, reusable experience edges, and adaptive escalation for reducing repeated retrieval tokens and latency.
Understand it in 90 seconds
-
RAG: Attach Retrieval to Generation, but Do Not Treat 2020 RAG as a Production RAG Platform
Intermediate Retrieval, memory, and production RAGA source-grounded reading of Lewis et al., NeurIPS 2020: BART is paired with a dense retriever over Wikipedia, and RAG-Sequence / RAG-Token condition generation on retrieved passages. RAG-Seq reaches 44.5 Exact Match on NQ; this is a 2020 method paper, not a 2025 production RAG platform and not an agent loop.
Understand it in 90 seconds
-
DPR: Turn Open-Domain QA into Dense Passage Retrieval, but Do Not Treat the Dual Encoder as Production RAG
Intermediate Retrieval, memory, and production RAGA source-grounded reading of Karpukhin et al., EMNLP 2020: a BERT dual encoder trained with question–passage pairs and in-batch negatives replaces BM25 over Wikipedia passages via MIPS. On NQ, top-20 retrieval is 78.4% vs BM25 59.1%; end-to-end Exact Match is 41.5. This is the retriever RAG uses, not a generation platform.
Understand it in 90 seconds
-
Self-RAG: Let the Model Decide When to Retrieve, but Do Not Treat Reflection Tokens as a Production RAG Gate
Intermediate Retrieval, memory, and production RAGA source-grounded reading of Asai et al., ICLR 2024: an LM is trained with reflection tokens (Retrieve / Relevant / Supported / Useful) for on-demand retrieval and self-critique. Self-RAG 7B / 13B reach 54.9 / 55.8 on PopQA; this is a when-to-retrieve method paper, not a production RAG platform and not an agent tool loop.
Understand it in 90 seconds
-
REALM: Wire Retrieval into LM Pre-Training, but Do Not Treat Joint Training as a Ready-Made RAG Stack
Intermediate Retrieval, memory, and production RAGA source-grounded reading of Guu et al., ICML 2020: a differentiable knowledge retriever is pre-trained with an MLM signal, an asynchronously refreshed MIPS index, and Open-QA fine-tuning. With CC-News / Wikipedia, NQ Exact Match is 40.4, above ORQA and T5-11B. This is costly retrieval-augmented pre-training—not Lewis RAG generation and not DPR’s cheaper dual-encoder recipe.
Understand it in 90 seconds
-
DocMemo: Letting Long-Document RAG Recover from a Bad First Retrieval
Advanced Retrieval, memory, and production RAGA deep reading of DocMemo: document schema, page belief, and question episodic memory preserve retrieval state across rounds, while Bayesian updates, Thompson sampling, and adaptive granularity recover missed evidence.
Understand it in 90 seconds
-
FinRank: Hard-Negative Retrieval Evaluation for Financial-Document RAG
Intermediate Retrieval, memory, and production RAGA deep reading of FinRank: how company, year, and disclosure boundaries create deceptively plausible evidence, and why pooled retrieval, hard negatives, and metadata filters must be evaluated together.
Understand it in 90 seconds
-
AskChem: Making Provenance-Carrying Claims the Retrieval Unit
Advanced Retrieval, memory, and production RAGA critical reading of AskChem's atomic claims, source locators, faceted taxonomy, evidence graph, and AskChem-Bench results, with a clear boundary between citation traceability and scientific correctness.
Understand it in 90 seconds
-
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Intermediate Retrieval, memory, and production RAGA deep reading of Wang et al.'s arXiv v3 study: across 28 nested enterprise-shaped corpus tiers with fixed questions, evidence, and adversarial documents, why BM25 crosses over at roughly 10 million corpus tokens and why agents should begin after global candidate discovery.
Understand it in 90 seconds
-
Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG
Advanced Retrieval, memory, and production RAGA deep read of how Before Reasoning Can Fail turns answer-before-reading into an observable trajectory failure, and tests whether Read-Gate actually improves multi-hop QA.
Understand it in 90 seconds
-
RubricRanker Deep Read: RAG Needs the Right Document Set, Not Just the Most Relevant Documents
Advanced Retrieval, memory, and production RAGA close reading of how RubricRanker uses query-specific search rubrics, SFT, and GRPO to train a document reranker, and what its deep-research and RAG benchmark results actually establish.
Understand it in 90 seconds
-
Beyond RAG for Agent Memory: Detailed Notes on xMemory
Intermediate Retrieval, memory, and production RAGAn interpretation of arXiv:2602.02007 covering xMemory's four-tier hierarchy, sparsity–semantics objective, two-stage top-down retrieval, and empirical results on LoCoMo/PerLTQA.
Understand it in 90 seconds
-
RAG vs GraphRAG: A Systematic Evaluation and Hybrid Strategies (Detailed Notes)
Intermediate Retrieval, memory, and production RAGInterpreting the unified evaluation protocol, four types of GraphRAG, figures in Tables 1-5, efficiency trade-offs, and Selection/Integration hybrid strategies based on arXiv:2502.11371.
Understand it in 90 seconds
-
RAG-Anything: Multimodal Document Retrieval Is Not Just Text Conversion
Intermediate Retrieval, memory, and production RAGA source-grounded reading of RAG-Anything's dual graph, experimental evidence, failure cases, artifact status, and engineering adoption boundary.
Understand it in 90 seconds
-
RAG-MCP: Retrieve Tool Discovery, but Account for Routing Failure
Intermediate Retrieval, memory, and production RAGA source-grounded reading of RAG-MCP's tool-routing pipeline, 11,100-tool stress test, MCPBench result, scale failure, and incomplete artifacts.
Understand it in 90 seconds
-
RAG without Forgetting: Writing Successful Query Expansion Back into the Index
Intermediate Retrieval, memory, and production RAGA source-grounded assessment of ERM's correctness gate, selective attribution, bounded key updates, BEIR/BRIGHT results, and missing artifacts.
Understand it in 90 seconds
For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.
Speaking & contact