{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/when-claims-evolve-evaluating-and-enhancing","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","arxiv_id":"2503.03417","date":"2025-03-05","proceeding":null,"authors":["Jabez Magomere","Emanuele La Malfa","Manuel Tonneau","Ashkan Kazemi","Scott Hale"],"abstract":"Online misinformation remains a critical challenge, and fact-checkers increasingly rely on embedding-based methods to retrieve relevant fact-checks. Yet, when debunked claims reappear in edited forms, the performance of these methods is unclear. In this work, we introduce a taxonomy of six common real-world misinformation edits and propose a perturbation framework that generates valid, natural claim variations. Our multi-stage retrieval evaluation reveals that standard embedding models struggle with user-introduced edits, while LLM-distilled embeddings offer improved robustness at a higher computational cost. Although a strong reranker helps mitigate some issues, it cannot fully compensate for first-stage retrieval gaps. Addressing these retrieval gaps, our train- and inference-time mitigation approaches enhance in-domain robustness by up to 17 percentage points and boost out-of-domain generalization by 10 percentage points over baseline models. Overall, our findings provide practical improvements to claim-matching systems, enabling more reliable fact-checking of evolving misinformation.","url_abs":"https://arxiv.org/abs/2503.03417v1","url_pdf":"https://arxiv.org/pdf/2503.03417v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"when-claims-evolve-evaluating-and-enhancing","repo_url":"https://github.com/JabezNzomo99/claim-matching-robustness","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"misinformation","task_name":"Misinformation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[{"slug":"claim-matching-robustness","name":"Claim Matching Robustness","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.03417","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}