Organizations: School of Information, Renmin University of China Beijing, China · School of Smart Governance, Renmin University of China Suzhou, China · School of Information, BRAIN, Renmin University of China Beijing, China · School of Economics and Management, Tsinghua University Beijing, China
The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowledge base. To address these challenges, this paper proposes QChunker, which restructures the RAG paradigm from retrieval-augmentation to understanding-retrieval-augmentation. Firstly, QChunker models the text chunking as a composite task of text segmentation and knowledge completion to ensure the logical coherence and integrity of text chunks. Drawing inspiration from Hal Gregersen's "Questions Are the Answer" theory, we design a multi-agent debate framework comprising four specialized components: a question outline generator, text segmenter, integrity reviewer, and knowledge completer. This framework operates on the principle that questions serve as catalysts for profound insights. Through this pipeline, we successfully construct a high-quality dataset of 45K entries and transfer this capability to small language models. Additionally, to handle long evaluation chains and low efficiency in existing chunking evaluation methods, which overly rely on downstream QA tasks, we introduce a novel direct evaluation metric, ChunkScore. Both theoretical and experimental validations demonstrate that ChunkScore can directly and efficiently discriminate the quality of text chunks. Furthermore, during the text segmentation phase, we utilize document outlines for multi-path sampling to generate multiple candidate chunks and select the optimal solution employing ChunkScore. Extensive experimental results across four heterogeneous domains exhibit that QChunker effectively resolves aforementioned issues by providing RAG with more logically coherent and information-rich text chunks.
Figures & tables
Figure 1. Overview of the QChunker framework’s multi-agent debate process. The workflow comprises four key stages: question outline generation, text segmentation, integrity review, and knowledge completion, followed by a concrete example.
Chunking Methods
CRUD
OmniEval
MultiFieldQA
HChemSafety
BLEU
ROU.
MET.
BLEU
ROU.
MET.
BLEU
ROU.
MET.
BLEU
ROU.
MET.
Original
0.5022
0.5654
0.7324
0.1906
0.2254
0.3904
0.1707
0.2315
0.3650
0.2282
0.2054
0.3152
Llama_index
0.5312
0.5896
0.7449
0.1969
0.2350
0.4040
0.1732
0.2363
0.3726
0.2477
0.2234
0.3213
Semantic Chunking
0.5188
0.5823
0.7434
0.1913
0.2240
0.3821
0.1609
0.2191
0.3468
0.2037
0.1891
0.2964
LumberChunker
0.5061
0.5701
0.7399
0.1997
0.2375
0.4085
0.1841
0.2426
0.3809
0.2298
0.2124
0.3402
MoC MetaChunker
0.5456
0.6031
0.7546
0.2042
0.2457
0.4141
0.1707
0.2255
0.3512
0.2525
0.2307
0.3449
Table 1. Main experimental results are presented in four domain QA datasets. ROU. and MET. represent ROUGE-L and METEOR, respectively. The best result is in bold, and the second best result is underlined.
Figure 2. Correlation analysis between ChunkScore and ROUGE-L performance on the CRUD Benchmark.
Figure 3. Trends in perplexity variations between original and rewritten text chunks across different LLMs.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure 4. Output example of the QChunker framework when processing chemical documents.
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 semantics of diverse texts. Despite its central role, chunking lacks a dedicated evaluation framework, making it difficult to assess and compare strategies independently of downstream performance. We challenge this paradigm by introducing Adaptive Chunking, a framework that selects the most suitable chunking strategy for each document based on a set of five novel intrinsic, document-based metrics: References Completeness (RC), Intrachunk Cohesion (ICC), Document Contextual Coherence (DCC), Block Integrity (BI), and Size Compliance (SC), which directly assess chunking quality across key dimensions. To support this framework, we also introduce two new chunkers, an LLM-regex splitter and a split-then-merge recursive splitter, alongside targeted post-processing techniques. On a diverse corpus spanning legal, technical, and social science domains, our metric-guided adaptive method significantly improves downstream RAG performance. Without changing models or prompts, our framework increases RAG outcomes, raising answers correctness to 72% (from 62-64%) and increasing the number of successfully answered questions by over 30% (65 vs. 49). These results demonstrate that adaptive, document-aware chunking, guided by a complementary suite of intrinsic metrics, offers a practical and effective path to more robust RAG systems. Code available at https://github.com/ekimetrics/adaptive-chunking.
Paulo Roberto de Moura Júnior, Jean Lelong, Annabelle Blangero
Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating ``semantic fragmentation'' that degrades downstream retrieval quality. In this paper, we propose TopoChunker, an agentic framework that maps heterogeneous documents onto a Structured Intermediate Representation (SIR) to explicitly preserve cross-segment dependencies. To balance structural fidelity with computational cost, TopoChunker employs a dual-agent architecture. An Inspector Agent dynamically routes documents through cost-optimized extraction paths, while a Refiner Agent performs capacity auditing and topological context disambiguation to reconstruct hierarchical lineage. Evaluated on unstructured narratives (GutenQA) and complex reports (GovReport), TopoChunker demonstrates state-of-the-art performance. It outperforms the strongest LLM-based baseline by 8.0% in absolute generation accuracy and achieves an 83.26% Recall@3, while simultaneously reducing token overhead by 23.5%, offering a scalable approach for structure-aware RAG.
Retrieval-Augmented Generation (RAG) systems depend critically on document chunking quality for retrieving relevant context. Fixed chunking segments documents into uniform units irrespective of semantics or user intent, producing a precision-recall trade-off unresolvable by tuning chunk size alone. Semantic and agentic methods partially address these limitations but do not integrate user queries at the chunking stage. We present Query-Adaptive Semantic Chunking (QASC), which dynamically constructs chunks by integrating queries into segmentation through three mechanisms: cosine similarity scoring between sentence and query embeddings to identify seed sentences, contextual window expansion around seeds to preserve coherence, and chunk-level score aggregation to ensure holistic relevance. We evaluate QASC on 100 technical documents across 200 queries spanning four types, comparing against fixed chunking at five granularities, recursive splitting, semantic chunking, and agentic chunking. QASC achieves an F1-score of 0.85, a relative improvement of 18-27% over fixed chunking and 8-12% over semantic and agentic alternatives. Ablation studies confirm each component contributes meaningfully. Human evaluation by three annotators (Cohen kappa = 0.82) corroborates that QASC produces more relevant and coherent chunks than existing methods.