cs.LGNov 9, 2026

Calibrating Document-Local Boundaries for Contextual Chunk Retrieval

Authors: Yuanxiang Wang, Hui Jiang, Da Zhu, Zhihua Chang

Organizations: Qwen Business Unit, Alibaba Group

Abstract

Late Chunking encodes an entire document before pooling at chunk boundaries, preserving document context in local retrieval units. Chunk-level post-training improves context-dependent retrieval, but shared context can make semantically similar same-document negatives difficult to distinguish. We study the local decision boundary between a gold chunk and its hardest sibling. Starting from InSeNT, we analyze InSeNT's within-document gradients and show that the entropy of the conditional negative allocation decreases monotonically with the scaling factor at fixed logits. We propose a two-part framework for calibrating document-local chunk boundaries. The first component adapts the discriminative scale from within-document margins, while the second exposes chunk partitions to attention during document encoding. Experiments on ConTEB and NanoBEIR show that the resulting model improves contextual chunk retrieval across the evaluated encoder settings while retaining competitive passage-level retrieval quality; ablations further characterize the distinct roles of adaptive scaling and chunk-aware routing.

Explore similar work

CardsList
  1. A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity

    Mar 7, 2026Muhammad Arslan Shaukat, Muntasir Adnan, Carlos C. N. KuhnDocument ChunkingDense Retrieval

  2. Contextual Embeddings Beyond the Gold Chunk

    Oct 28, 2026Sedigheh Eslami, Markus Krimmel, William Barber +7Text EmbeddingsText Embedding Models