%0 Conference Paper %1 benchert-etal-2025-caidas %A Benchert, Dominik %A Meßlinger, Severin %A Goller, Sven %A Kaiser, Jonas %A Pfister, Jan %A Hotho, Andreas %B Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) %C Vienna, Austria %D 2025 %E Rosenthal, Sara %E Rosá, Aiala %E Ghosh, Debanjan %E Zampieri, Marcos %I Association for Computational Linguistics %K nlp myown author:kaiser author:hotho from:janpf author:pfister %P 1623--1638 %T CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval %U https://aclanthology.org/2025.semeval-1.214/ %X The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53\% for the monolingual task and 74.48\% for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th). %@ 979-8-89176-273-2

@inproceedings{benchert-etal-2025-caidas, abstract = {The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53{\%} for the monolingual task and 74.48{\%} for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).}, added-at = {2025-08-08T13:18:45.000+0200}, address = {Vienna, Austria}, author = {Benchert, Dominik and Me{\ss}linger, Severin and Goller, Sven and Kaiser, Jonas and Pfister, Jan and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/2718b2f4d802274a1adf075edee15bc6b/dmir}, booktitle = {Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)}, editor = {Rosenthal, Sara and Ros{\'a}, Aiala and Ghosh, Debanjan and Zampieri, Marcos}, interhash = {ad9583887d374bd0715928d223b95fac}, intrahash = {718b2f4d802274a1adf075edee15bc6b}, isbn = {979-8-89176-273-2}, keywords = {nlp myown author:kaiser author:hotho from:janpf author:pfister}, month = jul, pages = {1623--1638}, publisher = {Association for Computational Linguistics}, timestamp = {2025-08-08T13:18:45.000+0200}, title = {{CAIDAS} at {S}em{E}val-2025 Task 7: Enriching Sparse Datasets with {LLM}-Generated Content for Improved Information Retrieval}, url = {https://aclanthology.org/2025.semeval-1.214/}, year = 2025 }