When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
cs.IR
Submitted: 2026-08-17
Updated: 2026-11-04
Code: https://github.com/casparil/chunking-eval2https:
Terminology
Sources
- Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis
- CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale
- The Faiss library
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Qwen3 Technical Report
- EmbeddingGemma: Powerful and Lightweight Text Representations
- Qwen2.5-1M Technical Report
- Evaluation of Retrieval-Augmented Generation: A Survey
- Arctic-Embed 2.0: Multilingual Retrieval Without Compromise
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA