Scholarlink

<p>Research contributions convey the essence of academic papers, highlighting the novel knowledge and understanding they provide compared to prior research. In this study, we address the challenge of extracting research contribution patterns automatically from citation sentences by proposing a tool-augmented LLM workflow, a novel framework that combines the precision of machine reading comprehension (MRC) with the contextual understanding and generative capabilities of LLM.</p><p>The workflow operates through three stages: (1) Citation Marker Identification, where LLM locate and extract citation markers; (2) Contribution Patterns Extraction, which uses MRC to generate context-specific queries and extract INNOVATION, INFLUENCE, and FIELD patterns; and (3) Contribution Summarization, where the extracted triples are synthesized into standardized, fluent academic statements while correcting subtle extraction errors by LLM.</p><p>Experimental results demonstrate that the proposed workflow outperforms generative baselines, suchas ChatGPT,by maintaining structural consistency, avoiding factual drift, and preserving per-reference granularity in multi-citation contexts. The modular, stage-wise architecture enhances interpretability and facilitates error recovery, making it well-suited for real-world scholarly applications. In particular, the MRC-based extraction module achieves substantial improvements over the state-of-the-art W<sup>2</sup>NER model, with gains of +23.76% inlabel-level F1-score and+31.92% inentity-level F1-score. This work provides a scalable, transparent, and high-precision solution for automated research contribution mining from academic literature.</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

A tool-augmented LLM workflow for automated research contribution patterns extraction from citation sentences

  • 期刊论文

  • 发表日期：

    2026年1月17日

查看全文
  • Yang Zhao,
  • Yue Xiao,
  • Yajiao Wang,
  • Zhixiong Zhang

摘要

Research contributions convey the essence of academic papers, highlighting the novel knowledge and understanding they provide compared to prior research. In this study, we address the challenge of extracting research contribution patterns automatically from citation sentences by proposing a tool-augmented LLM workflow, a novel framework that combines the precision of machine reading comprehension (MRC) with the contextual understanding and generative capabilities of LLM.

The workflow operates through three stages: (1) Citation Marker Identification, where LLM locate and extract citation markers; (2) Contribution Patterns Extraction, which uses MRC to generate context-specific queries and extract INNOVATION, INFLUENCE, and FIELD patterns; and (3) Contribution Summarization, where the extracted triples are synthesized into standardized, fluent academic statements while correcting subtle extraction errors by LLM.

Experimental results demonstrate that the proposed workflow outperforms generative baselines, suchas ChatGPT,by maintaining structural consistency, avoiding factual drift, and preserving per-reference granularity in multi-citation contexts. The modular, stage-wise architecture enhances interpretability and facilitates error recovery, making it well-suited for real-world scholarly applications. In particular, the MRC-based extraction module achieves substantial improvements over the state-of-the-art W2NER model, with gains of +23.76% inlabel-level F1-score and+31.92% inentity-level F1-score. This work provides a scalable, transparent, and high-precision solution for automated research contribution mining from academic literature.