Skip to content
← Back to explorer

KohakuRAG: A simple RAG framework with hierarchical document indexing

Shih-Ying Yeh, Yueh-Feng Ku, Ko-Wei Huang, Buu-Khang Tu · Mar 8, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 8, 2026, 12:52 PM

Recent

Extraction refreshed

Mar 14, 2026, 4:02 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection. We present KohakuRAG, a hierarchical RAG framework that preserves document structure through a four-level tree representation (document $\rightarrow$ section $\rightarrow$ paragraph $\rightarrow$ sentence) with bottom-up embedding aggregation, improves retrieval coverage through an LLM-powered query planner with cross-query reranking, and stabilizes answers through ensemble inference with abstention-aware voting. We evaluate on the WattBot 2025 Challenge, a benchmark requiring systems to answer technical questions from 32 documents with $\pm$0.1% numeric tolerance and exact source attribution. KohakuRAG achieves first place on both public and private leaderboards (final score 0.861), as the only team to maintain the top position across both evaluation partitions. Ablation studies reveal that prompt ordering (+80% relative), retry mechanisms (+69%), and ensemble voting with blank filtering (+1.2pp) each contribute substantially, while hierarchical dense retrieval alone matches hybrid sparse-dense approaches (BM25 adds only +3.1pp). We release KohakuRAG as open-source software at https://github.com/KohakuBlueleaf/KohakuRAG.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Reported Metrics

partial

Precision

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Ranking
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

precision

Research Brief

Deterministic synthesis

We present KohakuRAG, a hierarchical RAG framework that preserves document structure through a four-level tree representation (document \rightarrow section \rightarrow paragraph \rightarrow sentence) with bottom-up embedding aggregation,… HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 4:02 AM · Grounded in abstract + metadata only

Key Takeaways

  • We present KohakuRAG, a hierarchical RAG framework that preserves document structure through a four-level tree representation (document \rightarrow section \rightarrow paragraph…
  • We evaluate on the WattBot 2025 Challenge, a benchmark requiring systems to answer technical questions from 32 documents with \pm0.1% numeric tolerance and exact source…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (precision).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • We present KohakuRAG, a hierarchical RAG framework that preserves document structure through a four-level tree representation (document \rightarrow section \rightarrow paragraph \rightarrow sentence) with bottom-up embedding aggregation,…
  • We evaluate on the WattBot 2025 Challenge, a benchmark requiring systems to answer technical questions from 32 documents with \pm0.1% numeric tolerance and exact source attribution.
  • KohakuRAG achieves first place on both public and private leaderboards (final score 0.861), as the only team to maintain the top position across both evaluation partitions.

Why It Matters For Eval

  • We evaluate on the WattBot 2025 Challenge, a benchmark requiring systems to answer technical questions from 32 documents with \pm0.1% numeric tolerance and exact source attribution.
  • KohakuRAG achieves first place on both public and private leaderboards (final score 0.861), as the only team to maintain the top position across both evaluation partitions.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: precision

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote