Skip to content
← Back to explorer

A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity

Muhammad Arslan Shaukat, Muntasir Adnan, Carlos C. N. Kuhn · Mar 7, 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 7, 2026, 1:33 AM

Recent

Extraction refreshed

Mar 13, 2026, 8:29 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. In our study, 36 segmentation methods spanning fixed-size, semantic, structure-aware, hierarchical, adaptive, and LLM-assisted approaches are benchmarked across six diverse knowledge domains using five different embedding models. Retrieval performance is assessed using graded relevance scores from a state-of-the-art LLM evaluator, with Normalised DCG@5 as the primary metric (complemented by Hit@5 and MRR). Our experiments show that content-aware chunking significantly improves retrieval effectiveness over naive fixed-length splitting. The top-performing strategy, Paragraph Group Chunking, achieved the highest overall accuracy (mean nDCG@5~0.459) and substantially better top-rank hit rates (Precision@1~24%, Hit@5~59%). In contrast, simple fixed-size character chunking as baselines performed poorly (nDCG@5 < 0.244, Precision@1~2-3%). We observe pronounced domain-specific differences: dynamic token sizing is strongest in biology, physics and health, while paragraph grouping is strongest in legal and maths. Larger embedding models yield higher absolute scores but remain sensitive to suboptimal segmentation, indicating that better chunking and large embeddings provide complementary benefits. In addition to accuracy gains, we quantify the efficiency trade-offs of advanced chunking. Producing more, smaller chunks can increase index size and latency. Consequently, we identify methods (like dynamic chunking) that approach an optimal balance of effectiveness and efficiency. These findings establish chunking as a vital lever for improving retrieval performance and reliability.

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: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.

Reported Metrics

partial

Accuracy, Precision, Mrr, Ndcg, Hit@5, Latency, Relevance

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Retrieval performance is assessed using graded relevance scores from a state-of-the-art LLM evaluator, with Normalised DCG@5 as the primary metric (complemented by Hit@5 and MRR).

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Math, Law
  • 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

accuracyprecisionmrrndcghit@5latencyrelevance

Research Brief

Deterministic synthesis

We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 13, 2026, 8:29 PM · Grounded in abstract + metadata only

Key Takeaways

  • We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of…
  • In our study, 36 segmentation methods spanning fixed-size, semantic, structure-aware, hierarchical, adaptive, and LLM-assisted approaches are benchmarked across six diverse…

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 (accuracy, precision, mrr).

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 the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.
  • In our study, 36 segmentation methods spanning fixed-size, semantic, structure-aware, hierarchical, adaptive, and LLM-assisted approaches are benchmarked across six diverse knowledge domains using five different embedding models.
  • The top-performing strategy, Paragraph Group Chunking, achieved the highest overall accuracy (mean nDCG@5~0.459) and substantially better top-rank hit rates (Precision@1~24%, Hit@5~59%).

Why It Matters For Eval

  • We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems.
  • In our study, 36 segmentation methods spanning fixed-size, semantic, structure-aware, hierarchical, adaptive, and LLM-assisted approaches are benchmarked across six diverse knowledge domains using five different embedding models.

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: accuracy, precision, mrr, ndcg

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