Scholarlink

<p>Small Language Models offer an efficient alternative for structured information extraction. We present <b>SLM-MATRIX</b>, a multi-path collaborative reasoning and verification framework based on SLMs, designed to extract material names, numerical values, and physical units from materials science literature. The framework integrates three complementary reasoning paths: a multi-agent collaborative path, a generator–discriminator path, and a dual cross-verification path. SLM-MATRIX achieves an accuracy of 92.85% on the BulkModulus dataset and reaches 77.68% accuracy on the MatSynTriplet dataset, both outperforming conventional methods and single-path models. Moreover, experiments on general reasoning benchmarks such as GSM8K and SVAMP validate the framework’s strong generalization capability. Ablation studies evaluate the effects of agent number, Mixture-of-Agents (MoA) depth, and discriminator design on overall performance. Overall, SLM-MATRIX presents an effective approach for high-quality material information extraction in resource-constrained and offers new insights into structured scientific text understanding tasks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SLM-MATRIX: a multi-agent trajectory reasoning and verification framework for enhancing language models in materials data extraction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月19日

查看全文
  • Xin Li,
  • Zhixuan Huang,
  • Shu Quan,
  • Cheng Peng,
  • Xiaoming Ma

摘要

Small Language Models offer an efficient alternative for structured information extraction. We present SLM-MATRIX, a multi-path collaborative reasoning and verification framework based on SLMs, designed to extract material names, numerical values, and physical units from materials science literature. The framework integrates three complementary reasoning paths: a multi-agent collaborative path, a generator–discriminator path, and a dual cross-verification path. SLM-MATRIX achieves an accuracy of 92.85% on the BulkModulus dataset and reaches 77.68% accuracy on the MatSynTriplet dataset, both outperforming conventional methods and single-path models. Moreover, experiments on general reasoning benchmarks such as GSM8K and SVAMP validate the framework’s strong generalization capability. Ablation studies evaluate the effects of agent number, Mixture-of-Agents (MoA) depth, and discriminator design on overall performance. Overall, SLM-MATRIX presents an effective approach for high-quality material information extraction in resource-constrained and offers new insights into structured scientific text understanding tasks.