A Systematic Analysis of Chunking Strategies for Reliable Question Answering

• URL: http://arxiv.org/abs/2601.14123v1
• Date: Tue, 20 Jan 2026 16:19:58 GMT
• Title: A Systematic Analysis of Chunking Strategies for Reliable Question Answering
• Authors: Sofia Bennani, Charles Moslonka,
• Abstract summary: We study how document chunking choices impact the reliability of Retrieval-Augmented Generation systems.<n>We use a standard industrial setup: SPLADE retrieval and a Mistral-8B generator.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study how document chunking choices impact the reliability of Retrieval-Augmented Generation (RAG) systems in industry. While practice often relies on heuristics, our end-to-end evaluation on Natural Questions systematically varies chunking method (token, sentence, semantic, code), chunk size, overlap, and context length. We use a standard industrial setup: SPLADE retrieval and a Mistral-8B generator. We derive actionable lessons for cost-efficient deployment: (i) overlap provides no measurable benefit and increases indexing cost; (ii) sentence chunking is the most cost-effective method, matching semantic chunking up to ~5k tokens; (iii) a "context cliff" reduces quality beyond ~2.5k tokens; and (iv) optimal context depends on the goal (semantic quality peaks at small contexts; exact match at larger ones).

Related papers

• Context Attribution with Multi-Armed Bandit Optimization [11.715006981206844]
  We propose a novel framework that formulates context attribution as a multi-armed bandit (CMAB) problem.<n>We employ Combinatorial Thompson Sampling (CTS) to efficiently explore the exponentially large space of context subsets under a limited query budget.<n>Our method defines a reward function based on normalized token likelihoods, capturing how well a subset of segments supports the original model response.
  arXiv  Detail & Related papers  (2025-06-24T19:47:27Z)
• Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation [52.3707788779464]
  We introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD)<n>ARC-JSD enables efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling.<n> Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements.
  arXiv  Detail & Related papers  (2025-05-22T09:04:03Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• SAGE: A Framework of Precise Retrieval for RAG [9.889395372896153]
  Retrieval-augmented generation (RAG) has demonstrated significant proficiency in conducting question-answering tasks.<n>RAG methods segment the corpus without considering semantics, making it difficult to find relevant context.<n>We introduce a RAG framework (SAGE) to overcome these limitations.
  arXiv  Detail & Related papers  (2025-03-03T16:25:58Z)
• Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models [0.6827423171182154]
  Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains.<n>We propose a framework combining granular evaluation metrics with synthetic data generation to optimize domain-specific RAG performance.<n>Our empirical analysis reveals critical insights: smaller chunks (less than 10 tokens) improve precision by 31-42%.
  arXiv  Detail & Related papers  (2025-02-21T06:38:57Z)
• CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing [74.14816777318033]
  Collaborative Inference with Token-lEvel Routing (CITER) is a framework that enables efficient collaboration between small and large language models.<n>We formulate router training as a policy optimization, where the router receives rewards based on both the quality of predictions and the inference costs of generation.<n>Our experiments show that CITER reduces the inference costs while preserving high-quality generation, offering a promising solution for real-time and resource-constrained applications.
  arXiv  Detail & Related papers  (2025-02-04T03:36:44Z)
• Is Semantic Chunking Worth the Computational Cost? [0.0]
  This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks. The results show that the computational costs associated with semantic chunking are not justified by consistent performance gains.
  arXiv  Detail & Related papers  (2024-10-16T21:53:48Z)
• Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation [60.493180081319785]
  We propose a systematic way to estimate the capacity of a truncation sampling method by considering the trade-off between diversity and risk at each decoding step.<n>Our work offers a comprehensive comparison of existing truncation sampling methods and serves as a practical user guideline for their parameter selection.
  arXiv  Detail & Related papers  (2024-08-24T14:14:32Z)
• Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models [24.085614720512744]
  This study shows that large language models (LLMs) are vulnerable to changes in the number and arrangement of options in text classification. Key bottleneck arises from ambiguous decision boundaries and inherent biases towards specific tokens and positions. Our approach is grounded in the empirical observation that pairwise comparisons can effectively alleviate boundary ambiguity and inherent bias.
  arXiv  Detail & Related papers  (2024-06-11T06:53:19Z)
• LLoCO: Learning Long Contexts Offline [63.3458260335454]
  We propose LLoCO, a novel approach to processing long contexts. LLoCO learns contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens.
  arXiv  Detail & Related papers  (2024-04-11T17:57:22Z)
• Self-Evaluation Guided Beam Search for Reasoning [61.523627290397556]
  We introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of Large Language Model (LLM) We propose a decoding algorithm integrating the self-evaluation guidance via beam search. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34%$, $9.56%$, and $5.46%$ on the GSM8K, AQuA, and StrategyQA.
  arXiv  Detail & Related papers  (2023-05-01T02:37:59Z)
• What Makes Good In-Context Examples for GPT-$3$? [101.99751777056314]
  GPT-$3$ has attracted lots of attention due to its superior performance across a wide range of NLP tasks. Despite its success, we found that the empirical results of GPT-$3$ depend heavily on the choice of in-context examples. In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples.
  arXiv  Detail & Related papers  (2021-01-17T23:38:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.