paper-with-me

홈 › Papers

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

2025-06-10 · Dongge Han, Menglin Xia, Daniel Madrigal Diaz, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Del Carmen Hipolito Garcia, Jin Xu, Victor Rühle, Saravan Rajmohan

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.

📄 PDF Abstract BibTeX arXiv:2506.08669

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KMathmbpp

Similar Papers 제목 키워드 기반

The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints

2025-03-29 · Aden Haussmann

Multilingual Natural Language Generation (NLG) is challenging due to the lack of training data for low-resource languages. However, some low-resource languages have up to tens of millions of speakers globally, making it …

Table-to-Text GenerationText Generation

CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs

2026-01-16 · Yuanxiang Liu, Songze Li, Xiaoke Guo, Zhaoyan Gong 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations. While Knowledge Graphs (KGs) offer explicit grounding, existing paradigm…

Knowledge Graphs

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning

2024-12-13 · Jing Bi, Yuting Wu, Weiwei Xing, Zhenjie Wei

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Advances in prompt engineering and fine-tuning techniques have further enhanced their ability to address complex reasoni…

Prompt Engineering

Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training

2025-10-22 · Mehrdad Ghassabi, Sadra Hakim, Hamidreza Baradaran Kashani, Pedram Rostami arxiv

Enhancing reasoning capabilities in small language models is critical for specialized applications such as medical question answering, particularly in underrepresented languages like Persian. In this study, we employ Rei…

Reinforcement LearningQuestion Answering

Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis

2026-04-22 · Viet-Man Le, Thi Ngoc Trang Tran, Sebastian Lubos, Alexander Felfernig 외 arxiv

We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., concise constrained-language descriptions of feature hierarchies and con…