{"ID":2886380,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03475","arxiv_id":"2508.03475","title":"fact check AI at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-checked Claim Retrieval","abstract":"SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval is approached as a Learning-to-Rank task using a bi-encoder model fine-tuned from a pre-trained transformer optimized for sentence similarity. Training used both the source languages and their English translations for multilingual retrieval and only English translations for cross-lingual retrieval. Using lightweight models with fewer than 500M parameters and training on Kaggle T4 GPUs, the method achieved 92% Success@10 in multilingual and 80% Success@10 in 5th in crosslingual and 10th in multilingual tracks.","short_abstract":"SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval is approached as a Learning-to-Rank task using a bi-encoder model fine-tuned from a pre-trained transformer optimized for sentence similarity. Training used both the source languages and their English translations for multilingual retrieval...","url_abs":"https://arxiv.org/abs/2508.03475","url_pdf":"https://arxiv.org/pdf/2508.03475v1","authors":"[\"Pranshu Rastogi\"]","published":"2025-08-05T14:10:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Transformer\"]","has_code":false}