Large Language Models (LLMs) excel in mathematical reasoning due to their extensive parameters and training data, but their high computational demands hinder deployment. Distilling LLM reasoning into Smaller Language Models (SLMs, ≤ 1B parameters) is a potential solution, yet these models often struggle with calculation and semantic errors. Previous work introduced Program-of-Thought Distillation (PoTD) to reduce calculation mistakes. To tackle semantic errors, we propose Key-Point-Driven Mathematical Reasoning Distillation (KPDD), which improves SLM reasoning by splitting the problem-solving process into Key Points Extraction and Step-by-Step Solution. KPDD includes KPDD-CoT, generating Chain-of-Thought rationales, and KPDD-PoT, producing Program-of-Thought rationales. Experiments show KPDD-CoT enhances reasoning capabilities, while KPDD-PoT achieves state-of-the-art performance in mathematical tasks, effectively reducing misunderstanding errors and promoting the deployment of efficient, capable SLMs.

Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks. However, their substantial computational and memory demands, due to billions of parameters, hinder deployment in resource-constrained environments. A promising solution is knowledge distillation, where LLMs transfer reasoning capabilities to Small Language Models (SLMs, ≤ 1B parameters), enabling wider deployment on low-resource devices. Existing methods primarily focus on generating high-quality reasoning rationales for distillation datasets but often neglect the critical role of data quantity and quality. To address these challenges, we propose a Feedback-Driven Distillation (FDD) framework to enhance SLMs’ mathematical reasoning capabilities. In the initialization stage, a distillation dataset is constructed by prompting LLMs to pair mathematical problems with corresponding reasoning rationales. We classify problems into easy and hard categories based on SLM performance. For easy problems, LLMs generate more complex variations, while for hard problems, new questions of similar complexity are synthesized. In addition, we propose a multi-round distillation paradigm to iteratively enrich the distillation datasets, thereby progressively improving the mathematical reasoning abilities of SLMs. Experimental results demonstrate that our method can make SLMs achieve SOTA mathematical reasoning performance.

Abstract Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged as a key research area to address these challenges. This paper presents a survey of model compression techniques for LLMs. We cover methods like quantization, pruning, and knowledge distillation, highlighting recent advancements. We also discuss benchmarking strategies and evaluation metrics crucial for assessing compressed LLMs. This survey offers valuable insights for researchers and practitioners, aiming to enhance efficiency and real-world applicability of LLMs while laying a foundation for future advancements.

Differentiable Neural Architecture Search (DARTS) is becoming more and more popular among Neural Architecture Search (NAS) methods because of its high search efficiency and low compute cost. However, the stability of DARTS is very inferior, especially skip connections aggregation that leads to performance collapse. Though existing methods leverage Hessian eigenvalues to alleviate skip connections aggregation, they make DARTS unable to explore architectures with better performance. In the paper, we propose operation-level progressive differentiable neural architecture search (OPP-DARTS) to avoid skip connections aggregation and explore better architectures simultaneously. We first divide the search process into several stages during the search phase and increase candidate operations into the search space progressively at the beginning of each stage. It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations. Besides, to keep the competition between operations relatively fair and select the operation from the candidate operations set that makes training loss of the supernet largest. The experiment results indicate that our method is effective and efficient. Our method’s performance on CIFAR-10 is superior to the architecture found by standard DARTS, and the transferability of our method also surpasses standard DARTS. We further demonstrate the robustness of our method on three simple search spaces, i.e., S2, S3, S4, and the results show us that our method is more robust than standard DARTS. Our code is available at https://github.com/zxunyu/OPP-DARTS.