Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs

• URL: http://arxiv.org/abs/2606.08605v1
• Date: Sun, 07 Jun 2026 12:33:43 GMT
• Title: Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs
• Abstract summary: We present a multilingual fact-checking system deployed at Factiverse.<n>The system follows a modular pipeline with three stages: claim detection, evidence retrieval and re-ranking, and veracity prediction.<n>Experiments on production data spanning 114 languages for claim detection and 28 languages for veracity prediction show that task-specific fine-tuning provides strong and stable multilingual performance.
• Score: 8.830479021890577
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a multilingual fact-checking system deployed at Factiverse, designed for high-throughput and low-latency operation across diverse languages. The system follows a modular pipeline with three stages: claim detection, evidence retrieval and re-ranking, and veracity prediction. We fine-tune XLM-RoBERTa-Large for claim detection, mmBERT-base for three-label stance classification (Supports/Refutes/Mixed), and a SetFit-based multilingual re-ranker for claim--evidence matching. We compare these components against strong LLM baselines, including GPT-5.2, Claude Opus~4.6, and Qwen3-8b. Experiments on production data spanning 114 languages for claim detection and 28 languages for veracity prediction show that task-specific fine-tuning provides strong and stable multilingual performance, while the fine-tuned retrieval model remains competitive with modern proprietary embeddings. Same-hardware latency measurements further show large efficiency gains for encoder-based components, supporting their use in production deployments with tight cost and privacy constraints. Overall, compact fine-tuned, self-hosted models remain a practical and effective foundation for multilingual fact-checking at scale. Code and data used for this study are available at https://github.com/factiverse/factcheck-editor.

Related papers

• MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models [6.382707047064603]
  Multi-Check-Worthy dataset spans 16 languages, 7 topical domains, and 2 writing styles.<n>It consists of 123,722 samples, evenly distributed between noisy (informal) and structured (formal) texts, with balanced representation of check-worthy and non-check-worthy classes across all languages.
  arXiv  Detail & Related papers  (2026-02-18T09:28:53Z)
• When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA [46.50540400870401]
  PsiloQA is a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages.<n>Our dataset and results advance the development of scalable, fine-grained hallucination detection in multilingual settings.
  arXiv  Detail & Related papers  (2025-10-06T14:36:30Z)
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models [84.19366314925593]
  We propose a consistency-based data method to construct high-quality multilingual preference data.<n> Specifically, our method includes two parts: consistency-guided English reference selection and cross-lingual consistency-based multilingual preference data construction.
  arXiv  Detail & Related papers  (2025-09-10T12:40:49Z)
• When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification [14.187153195380668]
  Large language models have remarkable capabilities across many NLP tasks, but their effectiveness for multilingual claim verification with nuanced classification schemes remains understudied.<n>We evaluate five state-of-the-art language models on the X-Fact dataset, which spans 25 languages with seven distinct veracity categories.<n>Surprisingly, we find that XLM-R substantially outperforms all tested LLMs, achieving 57.7% macro-F1 compared to the best LLM performance of 16.9%.
  arXiv  Detail & Related papers  (2025-07-28T10:49:04Z)
• M-Prometheus: A Suite of Open Multilingual LLM Judges [65.63858815169924]
  We introduce M-Prometheus, a suite of open-weight LLM judges that can provide both direct assessment and pairwise comparison feedback on multilingual outputs.<n>M-Prometheus models outperform state-of-the-art open LLM judges on multilingual reward benchmarks spanning more than 20 languages, as well as on literary machine translation (MT) evaluation covering 4 language pairs.
  arXiv  Detail & Related papers  (2025-04-07T11:37:26Z)
• Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking [2.321323878201932]
  MultiSynFact is the first large-scale multilingual fact-checking dataset containing 2.2M claim-source pairs.<n>Our dataset generation pipeline leverages Large Language Models (LLMs), integrating external knowledge from Wikipedia.<n>We open-source a user-friendly framework to facilitate further research in multilingual fact-checking and dataset generation.
  arXiv  Detail & Related papers  (2025-02-21T12:38:26Z)
• On the Calibration of Multilingual Question Answering LLMs [57.296161186129545]
  We benchmark the calibration of several multilingual Large Language Models (MLLMs) on a variety of Question Answering tasks. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings. For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data.
  arXiv  Detail & Related papers  (2023-11-15T03:29:02Z)
• Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models [75.75038268227554]
  Self-Checker is a framework comprising a set of plug-and-play modules that facilitate fact-checking. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments.
  arXiv  Detail & Related papers  (2023-05-24T01:46:07Z)
• Multilingual Large Language Models Are Not (Yet) Code-Switchers [41.47534626749588]
  Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks. The practice of alternating languages within an utterance remains relatively uncharted. We argue that current "multilingualism" in LLMs does not inherently imply proficiency with code-switching texts.
  arXiv  Detail & Related papers  (2023-05-23T16:50:48Z)
• MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset [0.0]
  Sentence Boundary Detection (SBD) is one of the foundational building blocks of Natural Language Processing (NLP) We curated a diverse multilingual legal dataset consisting of over 130'000 annotated sentences in 6 languages. We trained and tested monolingual and multilingual models based on CRF, BiLSTM-CRF, and transformers, demonstrating state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-05-02T05:52:03Z)
• Are Multilingual Models Effective in Code-Switching? [57.78477547424949]
  We study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching.
  arXiv  Detail & Related papers  (2021-03-24T16:20:02Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.