{"slug": "turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero", "title": "Turkish Multimodal Video Fact-Checking: A New Dataset and a Comparison of Zero-Shot Agentic and Fine-Tuned Systems", "summary": "Researchers introduced TeViD, described as the first multimodal video fact-checking dataset for Turkish, built from articles published by IFCN-certified Teyit.org and enriched with translated Snopes articles and synthetic examples to reduce class imbalance. Using the same open-source base model, the researchers compared two pipelines: 3MFact-TR, which pairs Qwen2.5-7B with Qwen2-VL-7B and adds a semantic inconsistency checker, a 5W1H question manager and a bilingual evidence retriever that excludes fact-checking sites to prevent leakage, and a single Qwen2.5-7B fine-tuned with Low-Rank Adaptation (LoRA) to produce closed-book verdicts from the claim and the video's textual description. The work reports accuracy, macro F1, True class F1 and True class recall for both systems alongside ablation studies, addressing the near-total focus of existing fact-checking systems on English text.", "body_md": "arXiv:2611.08651v1 Announce Type: new \nAbstract: Video-based misinformation spreads rapidly on social media, but almost all existing fact-checking systems focus exclusively on English text. Tools for low-resource languages such as Turkish are severely limited. In this work, we present TeViD (Turkish Video Fact-checking Dataset), to the best of our knowledge the first multimodal video fact-checking dataset for Turkish. We compiled the dataset from articles published by Teyit.org, an IFCN-certified organisation, and enriched it with translated Snopes articles and synthetic examples to reduce class imbalance. Building on TeViD, we develop two verification pipelines that share the same open-source base model. First, in 3MFact-TR (Pipeline 1), we adapt the multi-role 3MFact framework to Turkish with the Qwen2.5-7B large language model and the Qwen2-VL-7B vision-language model, and add three modules of our own: a semantic inconsistency checker, a 5W1H question manager, and a bilingual evidence retriever that excludes fact-checking sites to prevent leakage. Second, as our Fine-Tuned Model (Pipeline 2), we fine-tune a single Qwen2.5-7B with Low-Rank Adaptation (LoRA) to produce closed-book verdicts from the claim and the video's textual description. We report accuracy, macro F1, True class F1, and True class recall for both systems, together with ablation studies.", "url": "https://wpnews.pro/news/turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero", "canonical_source": "https://arxiv.org/abs/2611.08651", "published_at": "2026-11-09 05:00:00+00:00", "updated_at": "2026-11-09 05:23:47.375224+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "natural-language-processing"], "entities": ["TeViD", "Teyit.org", "Snopes", "3MFact-TR", "Qwen2.5-7B", "Qwen2-VL-7B", "Low-Rank Adaptation"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero", "markdown": "https://wpnews.pro/news/turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero.md", "text": "https://wpnews.pro/news/turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero.txt", "jsonld": "https://wpnews.pro/news/turkish-multimodal-video-fact-checking-a-new-dataset-and-a-comparison-of-zero.jsonld"}}