基于关系特征零样本检索，精准定位论文引用目标。
Team LA at SCIDOCA shared task 2025: Citation Discovery via relation-based zero-shot retrieval
- 从段落中提取关系特征，筛选最相似候选论文
- 在10个候选中准确识别正确引用，显著提升匹配精度
- 适合需要自动化引文推荐的研究者和学术系统开发者
引文发现共享任务旨在为给定段落从候选论文池中预测正确的引用。主要挑战源于摘要长度和候选摘要间的高度相似性，导致难以精确判断应引用的论文。为此，我们构建了一个系统：首先基于段落提取的关系特征，检索出前k个最相似的摘要；随后在该子集中利用大语言模型（LLM）精确定位最相关的引用。我们在SCIDOCA 2025组织方提供的训练数据集上评估了该框架，验证了其在引文预测任务中的有效性。
原文摘要 · Abstract (English)
The Citation Discovery Shared Task focuses on predicting the correct citation from a given candidate pool for a given paragraph. The main challenges stem from the length of the abstract paragraphs and the high similarity among candidate abstracts, making it difficult to determine the exact paper to cite. To address this, we develop a system that first retrieves the top-k most similar abstracts based on extracted relational features from the given paragraph. From this subset, we leverage a Large Language Model (LLM) to accurately identify the most relevant citation. We evaluate our framework on the training dataset provided by the SCIDOCA 2025 organizers, demonstrating its effectiveness in citation prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。