Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach

• URL: http://arxiv.org/abs/2602.13890v1
• Date: Sat, 14 Feb 2026 21:17:44 GMT
• Title: Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach
• Authors: Amir Hossein Mohammadi, Ali Moeinian, Zahra Razavizade, Afsaneh Fatemi, Reza Ramezani,
• Abstract summary: Retrieval Augmented Generation (RAG) is a powerful approach for enhancing the factual grounding of language models by integrating external knowledge.<n>This paper presents a large-scale empirical study to investigate the influence of prompt template design on RAG performance.<n>Our findings, based on a test set of 18720 instances, reveal significant performance gains of up to 83% on Qwen2.5 and 84.5% on Gemma3-4B-It.
• Score: 9.672512327395435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval Augmented Generation (RAG) is a powerful approach for enhancing the factual grounding of language models by integrating external knowledge. While widely studied for large language models, the optimization of RAG for Small Language Models (SLMs) remains a critical research gap, particularly in complex, multi-hop question-answering tasks that require sophisticated reasoning. In these systems, prompt template design is a crucial yet under-explored factor influencing performance. This paper presents a large-scale empirical study to investigate this factor, evaluating 24 different prompt templates on the HotpotQA dataset. The set includes a standard RAG prompt, nine well-formed techniques from the literature, and 14 novel hybrid variants, all tested on two prominent SLMs: Qwen2.5-3B Instruct and Gemma3-4B-It. Our findings, based on a test set of 18720 instances, reveal significant performance gains of up to 83% on Qwen2.5 and 84.5% on Gemma3-4B-It, yielding an improvement of up to 6% for both models compared to the Standard RAG prompt. This research also offers concrete analysis and actionable recommendations for designing effective and efficient prompts for SLM-based RAG systems, practically for deployment in resource-constrained environments.

Related papers

• Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models [0.0]
  We present a controlled study of multi-hop contextual reasoning in large language models.<n>We show that multi-agent systems show the inverse pattern, achieving up to 80% on reasoning tasks where rule-based methods fail.
  arXiv  Detail & Related papers  (2026-01-06T20:18:55Z)
• LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation [12.734342155120979]
  We study reasoning strategies for reasoning models in RAG multi-hop QA tasks.<n>Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge.<n>We propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG.
  arXiv  Detail & Related papers  (2025-12-20T11:53:37Z)
• Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models [5.584522240405349]
  This study explores automatic generation (AIG) using language models to create multiple choice questions (MCQs) for morphological assessment.<n>We evaluated seven structured prompting strategies, including zero-shot, few-shot, chain-of-thought, role-based, sequential, and combinations.<n>Results show that structured prompting, especially strategies combining chain-of-thought and sequential design, significantly improved Gemma's outputs.
  arXiv  Detail & Related papers  (2025-08-27T18:54:32Z)
• Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field [0.0]
  This paper offers an analysis of the ability of large models to identify semantic relationships between different research topics.<n>We developed a gold standard based on the IEEE Thesaurus to evaluate the task.<n>Several models have achieved outstanding results, including Mixtral-8x7B, Dolphin-Mistral, and Claude 3-7B.
  arXiv  Detail & Related papers  (2024-12-11T10:11:41Z)
• FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research [70.6584488911715]
  retrieval-augmented generation (RAG) has attracted considerable research attention.<n>Existing RAG toolkits are often heavy and inflexibly, failing to meet the customization needs of researchers.<n>Our toolkit has implemented 16 advanced RAG methods and gathered and organized 38 benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-22T12:12:40Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models [56.256069117502385]
  Chain of Thought (CoT) approaches can be used to enhance the capability of Large Language Models (LLMs) on complex reasoning tasks. However, the selection of optimal CoT demonstration examples in multi-modal reasoning remains less explored. We introduce a novel approach that addresses this challenge by using retrieval mechanisms to automatically select demonstration examples.
  arXiv  Detail & Related papers  (2023-12-04T08:07:21Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)
• Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification [58.720142291102135]
  This case study investigates the task of job classification in a real-world setting. The goal is to determine whether an English-language job posting is appropriate for a graduate or entry-level position.
  arXiv  Detail & Related papers  (2023-03-13T14:09:53Z)

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.