用大模型重排序提升科学假说在社交媒体中的溯源效率
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
- 融合BM25与多语言检索模型，再经大模型重排序
- 英文开发集MRR@5达64.36%，超越基线13.67点
- 无需微调也能媲美专用模型，适合信息核查场景
科学假说常在社交媒体快速传播却缺乏原始学术来源链接。本文提出SciClaimSeekers系统，结合BM25与零样本多语言E5检索，通过倒数排名融合（k=60）后，使用Qwen2.5-14B-Instruct进行点对点重排序。该流程在CLEF-2026 CheckThat! Task 1的英文开发集上达到64.36% MRR@5，较BM25提升13.67个百分点，较未排序混合方法提升10.17个百分点；在官方测试集上取得64.39%的成绩。实验表明，经过精心设计的大型预训练模型流水线，在此任务上可与微调方法相媲美。
原文摘要 · Abstract (English)
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. The pipeline reaches 64.36% MRR@5 on the English development set a 13.67-point jump over BM25 and 10.17 points over the unranked hybrid and 64.39% on the official test set, in the CLEF-2026 CheckThat! Task 1 evaluation. Our experiment suggests that large pre-trained models, when combined into a careful pipeline, can be competitive with fine-tuned approaches on this task.
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。