Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search

• URL: http://arxiv.org/abs/2506.08669v1
• Date: Tue, 10 Jun 2025 10:30:43 GMT
• Title: Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
• Authors: Dongge Han, Menglin Xia, Daniel Madrigal Diaz, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Del Carmen Hipolito Garcia, Jin Xu, Victor Rühle, Saravan Rajmohan,
• Abstract summary: Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs)<n>Our framework integrates a prompt template search mechanism to mitigate the SLMs' sensitivity to prompt variations.<n>Our approach improves the reasoning capabilities of SLMs without increasing model size or requiring additional training.
• Score: 18.317836598695706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs). However, SLMs' limited capacity restricts their reasoning capabilities and makes them sensitive to prompt variations. To address these challenges, we propose a novel framework that enhances SLM reasoning capabilities through LLM generated blueprints. The blueprints provide structured, high-level reasoning guides that help SLMs systematically tackle related problems. Furthermore, our framework integrates a prompt template search mechanism to mitigate the SLMs' sensitivity to prompt variations. Our framework demonstrates improved SLM performance across various tasks, including math (GSM8K), coding (MBPP), and logic reasoning (BBH). Our approach improves the reasoning capabilities of SLMs without increasing model size or requiring additional training, offering a lightweight and deployment-friendly solution for on-device or resource-constrained environments.

Related papers

• Guiding Reasoning in Small Language Models with LLM Assistance [23.3038074903744]
  Small Language Models cast doubt suitability for tasks demanding deep, multi-step logical deduction.<n>This paper introduces a framework called Small Reasons, Large Hints, which selectively augments SLM reasoning with targeted guidance from large language models.<n>Our experiments on mathematical reasoning datasets demonstrate that targeted external scaffolding significantly improves performance.
  arXiv  Detail & Related papers  (2025-04-14T06:32:45Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Optimal Decision Making Through Scenario Simulations Using Large Language Models [0.0]
  Large Language Models (LLMs) have transformed how complex problems are approached and solved. This paper proposes an innovative approach to bridge this capability gap. By enabling LLMs to request multiple potential options and their respective parameters from users, our system introduces a dynamic framework. This function is designed to analyze the provided options, simulate potential outcomes, and determine the most advantageous solution.
  arXiv  Detail & Related papers  (2024-07-09T01:23:09Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Efficient Prompting for LLM-based Generative Internet of Things [88.84327500311464]
  Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. We propose a LLM-based Generative IoT (GIoT) system deployed in the local network setting in this study.
  arXiv  Detail & Related papers  (2024-06-14T19:24:00Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)<n>We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• When Emotional Stimuli meet Prompt Designing: An Auto-Prompt Graphical Paradigm [43.2625101868969]
  This paper summarizes the prompt words for large language models (LLMs) It then proposes an Auto-Prompt Graphical Paradigm(APGP) that combines both stimulating and framework prompts. The framework involves automated prompt generation and consideration of emotion-stimulus factors.
  arXiv  Detail & Related papers  (2024-04-16T12:19:08Z)
• Towards Pareto Optimal Throughput in Small Language Model Serving [4.497936996651617]
  Small Language Models (SLMs) offer new opportunities for resource-constrained users. We present a set of experiments designed to benchmark SLM inference at performance and energy levels.
  arXiv  Detail & Related papers  (2024-04-04T10:45:07Z)
• LLM Augmented LLMs: Expanding Capabilities through Composition [56.40953749310957]
  CALM -- Composition to Augment Language Models -- introduces cross-attention between models to compose their representations and enable new capabilities. We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13% on tasks like translation into English. When PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40% over the base model for code generation and explanation tasks.
  arXiv  Detail & Related papers  (2024-01-04T18:53:01Z)

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.