mlsanityData to 14 Oct 2026

MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment

arXiv 2512.20950 ↗First posted 24 Dec 2025cs.CL cs.AI cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a novel approach that leverages a dual-encoder architecture with contrastive learning and incorporates both native and English translations across different modalities. Our method effectively retrieves claims across multiple languages by learning the relative importance of different sources in alignment. To enhance robustness, we employ efficient data preprocessing and augmentation using large language models while incorporating hard negative sampling to improve representation learning. We evaluate our approach on monolingual and crosslingual benchmarks, demonstrating significant improvements in retrieval accuracy and fact-checking performance over baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 24 Dec 2025.

Builds on

16 of 32 references.

References · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  5. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  6. 2020That is a Known Lie: Detecting Previously Fact-Checked Claimscited by 82
  7. 2020Overview of CheckThat! 2020: Automatic Identification and Verification of Claims in Social Mediacited by 46
  8. 2021Claim Matching Beyond English to Scale Global Fact-Checkingcited by 42
  9. 2023Multilingual Previously Fact-Checked Claim Retrievalcited by 32
  10. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  11. 2021Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claimscited by 16
  12. 2025SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrievalcited by 11
4 more
  1. 2025Large Language Models for Multilingual Previously Fact-Checked Claim Detectioncited by 6
  2. 2022Harnessing Abstractive Summarization for Fact-Checked Claim Detectioncited by 5
  3. 2023Leveraging Social Discourse to Measure Check-worthiness of Claims for Fact-checkingcited by 2
  4. 2023Lost in translation: using global fact-checks to measure multilingual misinformation prevalence, spread, and evolutioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Multilingual, Multimodal Pipeline for Creating Authentic and Structured Fact-Checked Claim Dataset
  2. 2025Reasoning-Guided Claim Normalization for Noisy Multilingual Social Media Posts
  3. 2026Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking
  4. 2026Fair Fact-Checking: Closing the Cross-Lingual Gap in LLM Factual Judgement with RoSh
  5. 2025Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
  6. 2025Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs
  7. 2024Claim Verification in the Age of Large Language Models: A Survey
  8. 2026Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies