Claim2Vec: Embedding Fact-Check Claims for Multilingual Similarity and Clustering

2026-04-10

AI Summary

This work addresses the challenge of effectively representing and clustering semantically similar yet linguistically diverse rumor claims in multilingual fact-checking. We propose the first embedding model specifically designed for multilingual fact-checking claims, which fine-tunes a multilingual pretrained encoder via contrastive learning to construct an optimized semantic vector space that supports cross-lingual similarity computation and clustering. Experimental results demonstrate that our approach significantly outperforms 14 baseline embedding models and 7 clustering algorithms across three datasets, achieving notable improvements in both cluster label alignment and the geometric structure of the embedding space, thereby enabling effective cross-lingual knowledge transfer.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recurrent claims present a major challenge for automated fact-checking systems designed to combat misinformation, especially in multilingual settings. While tasks such as claim matching and fact-checked claim retrieval aim to address this problem by linking claim pairs, the broader challenge of effectively representing groups of similar claims that can be resolved with the same fact-check via claim clustering remains relatively underexplored. To address this gap, we introduce Claim2Vec, the first multilingual embedding model optimized to represent fact-check claims as vectors in an improved semantic embedding space. We fine-tune a multilingual encoder using contrastive learning with similar multilingual claim pairs. Experiments on the claim clustering task using three datasets, 14 multilingual embedding models, and 7 clustering algorithms demonstrate that Claim2Vec significantly improves clustering performance. Specifically, it enhances both cluster label alignment and the geometric structure of the embedding space across different cluster configurations. Our multilingual analysis shows that clusters containing multiple languages benefit from fine-tuning, demonstrating cross-lingual knowledge transfer.

Problem

• fact-checking
• claim clustering
• multilingual
• misinformation
• semantic representation

Innovation

• Claim2Vec
• multilingual embedding
• contrastive learning
• claim clustering
• cross-lingual transfer