Word2winners at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
Not on the map. Why?
Abstract (arXiv)
This paper describes our system for SemEval 2025 Task 7: Previously Fact-Checked Claim Retrieval. The task requires retrieving relevant fact-checks for a given input claim from the extensive, multilingual MultiClaim dataset, which comprises social media posts and fact-checks in several languages. To address this challenge, we first evaluated zero-shot performance using state-of-the-art English and multilingual retrieval models and then fine-tuned the most promising systems, leveraging machine translation to enhance crosslingual retrieval. Our best model achieved an accuracy of 85% on crosslingual data and 92% on monolingual data.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 15 references that are in the map. First posted on arXiv 12 Mar 2025.
Builds on
9 of 15 references.
References · 9
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2020Language-agnostic BERT Sentence Embeddingcited by 627
- 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
- 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 347
- 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
- 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 125
- 2021Claim Matching Beyond English to Scale Global Fact-Checkingcited by 42
- 2024Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Researchcited by 35
- 2023Multilingual Previously Fact-Checked Claim Retrievalcited by 32
Built on by
Citing papers per year: 2025: 1.
1 paper.