# Enhancing Retrieval-Augmented Generation: A Study of Best Practices

arXiv: https://arxiv.org/abs/2501.07391 · HTML: https://mlsanity.com/paper/2501.07391/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [Searching for Best Practices in Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01219/) (2024)
- [Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases](https://mlsanity.com/paper/2403.10446/) (2024)
- [WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia](https://mlsanity.com/paper/2305.14292/) (2023)
- [Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?](https://mlsanity.com/paper/2405.06105/) (2024)
- [NEWTS: A Corpus for News Topic-Focused Summarization](https://mlsanity.com/paper/2205.15661/) (2022)
- [RAGGED: Towards Informed Design of Scalable and Stable RAG Systems](https://mlsanity.com/paper/2403.09040/) (2024)
- [LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding](https://mlsanity.com/paper/2403.14252/) (2024)
- [Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics](https://mlsanity.com/paper/2403.08904/) (2024)
- [Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives](https://mlsanity.com/paper/2305.08088/) (2023)
- [Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2405.04713/) (2024)

## Built on by (most cited first, 23 of 23)

- [Get Experience from Practice: LLM Agents with Record & Replay](https://mlsanity.com/paper/2505.17716/) (2025)
- [FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.15800/) (2025)
- [Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks](https://mlsanity.com/paper/2508.17744/) (2025)
- [Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain](https://mlsanity.com/paper/2509.03787/) (2025)
- [Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis](https://mlsanity.com/paper/2504.05324/) (2025)
- [Less LLM, More Documents: Searching for Improved RAG](https://mlsanity.com/paper/2510.02657/) (2025)
- [Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation](https://mlsanity.com/paper/2506.20869/) (2025)
- [LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction](https://mlsanity.com/paper/2507.04748/) (2025)
- [A Large-Language-Model Framework for Automated Humanitarian Situation Reporting](https://mlsanity.com/paper/2512.19475/) (2025)
- [From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents](https://mlsanity.com/paper/2604.01733/) (2026)
- [Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources](https://mlsanity.com/paper/2606.28370/) (2026)
- [A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain](https://mlsanity.com/paper/2511.07577/) (2025)
- [AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows](https://mlsanity.com/paper/2602.00052/) (2026)
- [Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts](https://mlsanity.com/paper/2602.09442/) (2026)
- [VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval](https://mlsanity.com/paper/2607.18098/) (2026)
- [A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation](https://mlsanity.com/paper/2502.20854/) (2025)
- [A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction](https://mlsanity.com/paper/2505.21109/) (2025)
- [Advancing Shared and Multi-Agent Autonomy in Underwater Missions: Integrating Knowledge Graphs and Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.20370/) (2025)
- [AI Engineering Blueprint for On-Premises Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2604.01395/) (2026)
- [Multimodal QUD: Inquisitive Questions from Scientific Figures](https://mlsanity.com/paper/2604.23733/) (2026)
- [Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering](https://mlsanity.com/paper/2607.06641/) (2026)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026)
- [Configuring RAG Systems: What Breaks, Where Originates, and How to Fix](https://mlsanity.com/paper/2610.18567/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems have recently shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses. However, the influence of various components and configurations within RAG systems remains underexplored. A comprehensive understanding of these elements is essential for tailoring RAG systems to complex retrieval tasks and ensuring optimal performance across diverse applications. In this paper, we develop several advanced RAG system designs that incorporate query expansion, various novel retrieval strategies, and a novel Contrastive In-Context Learning RAG. Our study systematically investigates key factors, including language model size, prompt design, document chunk size, knowledge base size, retrieval stride, query expansion techniques, Contrastive In-Context Learning knowledge bases, multilingual knowledge bases, and Focus Mode retrieving relevant context at sentence-level. Through extensive experimentation, we provide a detailed analysis of how these factors influence response quality. Our findings offer actionable insights for developing RAG systems, striking a balance between contextual richness and retrieval-generation efficiency, thereby paving the way for more adaptable and high-performing RAG frameworks in diverse real-world scenarios. Our code and implementation details are publicly available.