UWBa at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
Not on the map. Why?
Abstract (arXiv)
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).
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 20 references that are in the map. First posted on arXiv 13 Aug 2025.
Builds on
7 of 20 references.
References · 7
- 2017Attention Is All You Needcited by 60,361
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
- 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
- 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 236
- 2023Multilingual Previously Fact-Checked Claim Retrievalcited by 32
- 2025SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrievalcited by 11
Built on by
Not cited yet.