Hierarchical vs. Sliding Window Chunking in Longformer Long-Range Reasoning on HotpotQA

Abstract

Abstract: This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does hierarchical chunking compare to sliding window strategies in preserving long-range reasoning accuracy for Longformer on the HotpotQA benchmark. The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to capture the nuanced structure and. 13 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 6.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does hierarchical chunking compare to sliding window strategies in preserving long-range reasoning accuracy for Longformer on the HotpotQA benchmark?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance