用大模型嵌入实现零样本事实核查检索，跨语言表现优异
UWBa at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
- 通过融合多个大模型嵌入，利用余弦相似度匹配最相关声明
- NV-Embed-v2在单语任务中排名第七，跨语言任务第九
- 仅用英文翻译输入，对部分语言组合模型效果更佳
本文提出一种零样本事实核查声明检索系统。我们采用多个最先进的大语言模型生成文本嵌入，并通过模型融合获得最优结果。该方法在单语子任务中取得第7名，在跨语言子任务中排名第9。由于多语言模型表现不理想，所有输入均使用英文翻译。通过嵌入向量与余弦相似度计算，识别每条帖子最相关的声明。最佳结果由NVIDIA NV-Embed-v2模型获得；对于某些语言，混合使用NV-Embed与GPT或Mistral模型进一步提升性能。
原文摘要 · Abstract (English)
This paper presents a zero-shot system for fact-checked claim retrieval. We employed several state-of-the-art large language models to obtain text embeddings. The models were then combined to obtain the best possible result. Our approach achieved 7th place in monolingual and 9th in cross-lingual subtasks. We used only English translations as an input to the text embedding models since multilingual models did not achieve satisfactory results. We identified the most relevant claims for each post by leveraging the embeddings and measuring cosine similarity. Overall, the best results were obtained by the NVIDIA NV-Embed-v2 model. For some languages, we benefited from model combinations (NV-Embed & GPT or Mistral).
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。