Little Brains, Big Feats: Exploring Compact Language Models

• URL: http://arxiv.org/abs/2606.30062v1
• Date: Mon, 29 Jun 2026 09:55:01 GMT
• Title: Little Brains, Big Feats: Exploring Compact Language Models
• Abstract summary: This study investigates how smaller language models perform during the generation stage within a Retrieval-Augmented Generation (RAG) system.<n>To benchmark these models effectively, we utilised both open-source and proprietary datasets covering diverse subject areas and question types.<n>Our findings demonstrate that a RAG system with small language models can be executed directly on-device without requiring any GPU hardware within a reasonable time.
• Score: 0.09236074230806579
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models have been dominating the research landscape recently, small language models remain highly relevant across various domains; yet, they receive far less attention. In this study, we investigate how smaller language models perform during the generation stage within a Retrieval-Augmented Generation (RAG) system. To benchmark these models effectively, we utilised both open-source and proprietary datasets covering diverse subject areas and question types. Our findings demonstrate that a RAG system with small language models can be executed directly on-device without requiring any GPU hardware within a reasonable time. The experimental code and links to the supplementary materials can be accessed through the GitHub repository: https://github.com/SibNN/SLM-RAG-EVAL.

Related papers

• ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting [0.8307668828380427]
  We show that two-tower encoder models are superior to one-tower encoders in low-resource settings for discriminative English tasks.<n>We also present ESsEN, a compact vision-language model that can be trained end-to-end with relatively few resources.
  arXiv  Detail & Related papers  (2026-04-20T16:10:28Z)
• The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering [19.009534602200862]
  We investigate the capabilities of existing integration methods for small language models (SLMs) in KG-based question answering.<n>To address this limitation, we propose leveraging simple and efficient exploration modules.<n>Experiment results demonstrate that these lightweight modules effectively improve the performance of small language models.
  arXiv  Detail & Related papers  (2025-09-09T05:26:29Z)
• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• UniRAG: Universal Retrieval Augmentation for Large Vision Language Models [76.30799731147589]
  We introduce UniRAG, a plug-and-play technique that adds relevant retrieved information to prompts as few-shot examples during inference.<n>Unlike the common belief that Retrieval Augmentation (RA) mainly improves generation or understanding of uncommon entities, our evaluation results on the MSCOCO dataset with common entities show that both proprietary models and smaller open-source models significantly enhance their generation quality.
  arXiv  Detail & Related papers  (2024-05-16T17:58:45Z)
• Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification [4.4467858321751015]
  We benchmark language models from 77M to 40B parameters using different architectures and scoring functions. Our findings reveal that small models can effectively classify texts, getting on par with or surpassing their larger counterparts. This research underscores the notion that bigger isn't always better, suggesting that resource-efficient small models may offer viable solutions for specific data classification challenges.
  arXiv  Detail & Related papers  (2024-04-17T07:10:28Z)
• Evaluating Large Language Models on Controlled Generation Tasks [92.64781370921486]
  We present an extensive analysis of various benchmarks including a sentence planning benchmark with different granularities. After comparing large language models against state-of-the-start finetuned smaller models, we present a spectrum showing large language models falling behind, are comparable, or exceed the ability of smaller models.
  arXiv  Detail & Related papers  (2023-10-23T03:48:24Z)
• Are Large Language Models Robust Coreference Resolvers? [17.60248310475889]
  We show that prompting for coreference can outperform current unsupervised coreference systems. Further investigations reveal that instruction-tuned LMs generalize surprisingly well across domains, languages, and time periods.
  arXiv  Detail & Related papers  (2023-05-23T19:38:28Z)
• Multi-lingual Evaluation of Code Generation Models [82.7357812992118]
  We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages. We are able to assess the performance of code generation models in a multi-lingual fashion.
  arXiv  Detail & Related papers  (2022-10-26T17:17:06Z)
• MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text [58.655375327681774]
  We propose the first Multimodal Retrieval-Augmented Transformer (MuRAG) MuRAG accesses an external non-parametric multimodal memory to augment language generation. Our results show that MuRAG achieves state-of-the-art accuracy, outperforming existing models by 10-20% absolute on both datasets.
  arXiv  Detail & Related papers  (2022-10-06T13:58:03Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)

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.