HiFACTMix: A Code-Mixed Benchmark and Graph-Aware Model for EvidenceBased Political Claim Verification in Hinglish

• URL: http://arxiv.org/abs/2508.10001v1
• Date: Mon, 04 Aug 2025 17:14:03 GMT
• Title: HiFACTMix: A Code-Mixed Benchmark and Graph-Aware Model for EvidenceBased Political Claim Verification in Hinglish
• Authors: Rakesh Thakur, Sneha Sharma, Gauri Chopra,
• Abstract summary: Existing fact-verification systems fail to generalize to real-world political discourse in linguistically diverse regions like India.<n>HiFACTMix is a novel graphaware, retrieval-augmented fact-checking model that combines multilingual contextual encoding, claim-evidence semantic alignment, evidence graph construction, graph neural reasoning, and natural language explanation generation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fact-checking in code-mixed, low-resource languages such as Hinglish remains an underexplored challenge in natural language processing. Existing fact-verification systems largely focus on high-resource, monolingual settings and fail to generalize to real-world political discourse in linguistically diverse regions like India. Given the widespread use of Hinglish by public figures, particularly political figures, and the growing influence of social media on public opinion, there's a critical need for robust, multilingual and context-aware fact-checking tools. To address this gap a novel benchmark HiFACT dataset is introduced with 1,500 realworld factual claims made by 28 Indian state Chief Ministers in Hinglish, under a highly code-mixed low-resource setting. Each claim is annotated with textual evidence and veracity labels. To evaluate this benchmark, a novel graphaware, retrieval-augmented fact-checking model is proposed that combines multilingual contextual encoding, claim-evidence semantic alignment, evidence graph construction, graph neural reasoning, and natural language explanation generation. Experimental results show that HiFACTMix outperformed accuracy in comparison to state of art multilingual baselines models and provides faithful justifications for its verdicts. This work opens a new direction for multilingual, code-mixed, and politically grounded fact verification research.

Related papers

• Code-Mix Sentiment Analysis on Hinglish Tweets [1.0998375857698497]
  Brand monitoring in India is increasingly challenged by the rise of Hinglish.<n>Traditional Natural Language Processing models often fail to interpret the syntactic and semantic complexity of this code-mixed language.<n>We propose a high-performance sentiment classification framework specifically designed for Hinglish tweets.
  arXiv  Detail & Related papers  (2026-01-08T16:39:26Z)
• Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG [55.258582772528506]
  We investigate whether the mixture of different document languages impacts generation and citation in unintended ways.<n>Across eight languages and six open-weight models, we find that models preferentially cite English sources when queries are in English.<n>We find that models sometimes trade-off document relevance for language preference, indicating that citation choices are not always driven by informativeness alone.
  arXiv  Detail & Related papers  (2025-09-17T12:58:18Z)
• Towards Explainable Bilingual Multimodal Misinformation Detection and Localization [64.37162720126194]
  BiMi is a framework that jointly performs region-level localization, cross-modal and cross-lingual consistency detection, and natural language explanation for misinformation analysis.<n>BiMiBench is a benchmark constructed by systematically editing real news images and subtitles.<n>BiMi outperforms strong baselines by up to +8.9 in classification accuracy, +15.9 in localization accuracy, and +2.5 in explanation BERTScore.
  arXiv  Detail & Related papers  (2025-06-28T15:43:06Z)
• Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models [1.835004446596942]
  We introduce a novel, manually annotated dataset of 2 thousand Telugu-English and 5 Nepali-English code-mixed comments.<n>The dataset undergoes rigorous preprocessing before being evaluated across multiple Machine Learning (ML), Deep Learning (DL), and Large Language Models (LLMs)<n>Our findings provide key insights into the challenges of detecting abusive language in code-mixed settings.
  arXiv  Detail & Related papers  (2025-04-23T11:29:10Z)
• Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages [0.0]
  In multilingual societies like India, text often exhibits code-mixing, blending local languages with English at different linguistic levels.<n>This paper introduces a prompt based method for a shared task aimed at addressing word-level LI challenges in Dravidian languages.<n>In this work, we leveraged GPT-3.5 Turbo to understand whether the large language models is able to correctly classify words into correct categories.
  arXiv  Detail & Related papers  (2024-11-06T16:20:37Z)
• NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages [54.808217147579036]
  We conduct a case study on Indonesian local languages. We compare the effectiveness of online scraping, human translation, and paragraph writing by native speakers in constructing datasets. Our findings demonstrate that datasets generated through paragraph writing by native speakers exhibit superior quality in terms of lexical diversity and cultural content.
  arXiv  Detail & Related papers  (2023-09-19T14:42:33Z)
• Claim Matching Beyond English to Scale Global Fact-Checking [5.836354423653351]
  We construct a novel dataset of WhatsApp tipline and public group messages alongside fact-checked claims. Our dataset contains content in high-resource (English, Hindi) and lower-resource (Bengali, Malayalam, Tamil) languages. We train our own embedding model using knowledge distillation and a high-quality "teacher" model in order to address the imbalance in embedding quality between the low- and high-resource languages.
  arXiv  Detail & Related papers  (2021-06-01T23:28:05Z)
• Role of Artificial Intelligence in Detection of Hateful Speech for Hinglish Data on Social Media [1.8899300124593648]
  Prevalence of Hindi-English code-mixed data (Hinglish) is on the rise with most of the urban population all over the world. Hate speech detection algorithms deployed by most social networking platforms are unable to filter out offensive and abusive content posted in these code-mixed languages. We propose a methodology for efficient detection of unstructured code-mix Hinglish language.
  arXiv  Detail & Related papers  (2021-05-11T10:02:28Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning [68.57658225995966]
  Cross-lingual Choice of Plausible Alternatives (XCOPA) is a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods falls short compared to translation-based transfer.
  arXiv  Detail & Related papers  (2020-05-01T12:22:33Z)

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.