The detection of hallucinations in multilingual scientific text generated by Large Language Models (LLMs) presents significant challenges for reliable AI systems. This paper describes our submission to the SHROOM-CAP 2025 shared task on scientific hallucination detection across 9 languages. Unlike most approaches that focus primarily on model architecture, we adopted a data-centric strategy that addressed the critical issue of training data scarcity and imbalance. We unify and balance five existing datasets to create a comprehensive training corpus of 124,821 samples (50% correct, 50% hallucinated), representing a 172x increase over the original SHROOM training data. Our approach fine-tuned XLM-RoBERTa-Large with 560 million parameters on this enhanced dataset, achieves competitive performance across all languages, including \textbf{2nd place in Gujarati} (zero-shot language) with Factuality F1 of 0.5107, and rankings between 4th-6th place across the remaining 8 languages. Our results demonstrate that systematic data curation can significantly outperform architectural innovations alone, particularly for low-resource languages in zero-shot settings.

Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We augment this data with carefully filtered backtranslated examples generated from monolingual Gujarati text. Surprisingly, adding this synthetic data does not improve translation performance and, in some cases, slightly reduces it. We evaluate our models using multiple metrics like BLEU, ChrF++, TER, BLEURT and analyze possible reasons for this saturation. Our findings suggest that backtranslation may reach a point of diminishing returns in certain low-resource settings and we discuss implications for future research.

Known by more than 1.5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to their rich cultural heritage, linguistic diversity, and complex structures. IndicMMLU-Pro is a comprehensive benchmark designed to evaluate Large Language Models (LLMs) across Indic languages, building upon the MMLU Pro (Massive Multitask Language Understanding) framework. Covering major languages such as Hindi, Bengali, Gujarati, Marathi, Kannada, Punjabi, Tamil, Telugu, and Urdu, our benchmark addresses the unique challenges and opportunities presented by the linguistic diversity of the Indian subcontinent. This benchmark encompasses a wide range of tasks in language comprehension, reasoning, and generation, meticulously crafted to capture the intricacies of Indian languages. IndicMMLU-Pro provides a standardized evaluation framework to push the research boundaries in Indic language AI, facilitating the development of more accurate, efficient, and culturally sensitive models. This paper outlines the benchmarks' design principles, task taxonomy, and data collection methodology, and presents baseline results from state-of-the-art multilingual models.

This paper presents an evaluation of the mathematical capability of ChatGPT across diverse languages like Hindi, Gujarati, and Marathi. ChatGPT, based on GPT-3.5 by OpenAI, has garnered significant attention for its natural language understanding and generation abilities. However, its performance in solving mathematical problems across multiple natural languages remains a comparatively unexplored area, especially in regional Indian languages. In this paper, we explore those capabilities as well as using chain-of-thought prompting to figure out if it increases the accuracy of responses as much as it does in the English language and provide insights into the current limitations.

In this paper, we explore the utility of Translationese as synthetic data created using machine translation for pre-training language models (LMs). Pre-training requires vast amounts of monolingual data, which is mostly unavailable for languages other than English. Recently, there has been a growing interest in using synthetic data to address this data scarcity. We take the case of English and Indic languages and translate web-crawled monolingual documents (clean) into the target language. Then, we train language models containing 28M and 85M parameters on this translationese data (synthetic). We show that their performance on downstream natural language understanding and generative tasks is only 3.56% poorer on NLU tasks and 1.51% on NLG tasks than LMs pre-trained on clean data. Further, we propose the use of lightweight TinyLMs pre-trained on clean data to filter synthetic data efficiently which significantly improves the performance of our models. We also find that LMs trained on synthetic data strongly benefit from extended pretraining on a tiny fraction (10%) of clean data. We release the data we collected and created as a part of this work, IndicMonoDoc, the largest collection of monolingual document-level corpora, which we hope will help bridge the gap between English and non-English performance for large language models.

Social media platforms serve as accessible outlets for individuals to express their thoughts and experiences, resulting in an influx of user-generated data spanning all age groups. While these platforms enable free expression, they also present significant challenges, including the proliferation of hate speech and offensive content. Such objectionable language disrupts objective discourse and can lead to radicalization of debates, ultimately threatening democratic values. Consequently, organizations have taken steps to monitor and curb abusive behavior, necessitating automated methods for identifying suspicious posts. This paper contributes to Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC) 2023 shared tasks track. We, team Z-AGI Labs, conduct a comprehensive comparative analysis of hate speech classification across five distinct languages: Bengali, Assamese, Bodo, Sinhala, and Gujarati. Our study encompasses a wide range of pre-trained models, including Bert variants, XLM-R, and LSTM models, to assess their performance in identifying hate speech across these languages. Results reveal intriguing variations in model performance. Notably, Bert Base Multilingual Cased emerges as a strong performer across languages, achieving an F1 score of 0.67027 for Bengali and 0.70525 for Assamese. At the same time, it significantly outperforms other models with an impressive F1 score of 0.83009 for Bodo. In Sinhala, XLM-R stands out with an F1 score of 0.83493, whereas for Gujarati, a custom LSTM-based model outshined with an F1 score of 0.76601. This study offers valuable insights into the suitability of various pre-trained models for hate speech detection in multilingual settings. By considering the nuances of each, our research contributes to an informed model selection for building robust hate speech detection systems.

Multilingual language models have shown impressive cross-lingual transfer ability across a diverse set of languages and tasks. To improve the cross-lingual ability of these models, some strategies include transliteration and finer-grained segmentation into characters as opposed to subwords. In this work, we investigate lexical sharing in multilingual machine translation (MT) from Hindi, Gujarati, Nepali into English. We explore the trade-offs that exist in translation performance between data sampling and vocabulary size, and we explore whether transliteration is useful in encouraging cross-script generalisation. We also verify how the different settings generalise to unseen languages (Marathi and Bengali). We find that transliteration does not give pronounced improvements and our analysis suggests that our multilingual MT models trained on original scripts seem to already be robust to cross-script differences even for relatively low-resource languages

The ILSUM shared task focuses on text summarization for two major Indian languages- Hindi and Gujarati, along with English. In this task, we experiment with various pretrained sequence-to-sequence models to find out the best model for each of the languages. We present a detailed overview of the models and our approaches in this paper. We secure the first rank across all three sub-tasks (English, Hindi and Gujarati). This paper also extensively analyzes the impact of k-fold cross-validation while experimenting with limited data size, and we also perform various experiments with a combination of the original and a filtered version of the data to determine the efficacy of the pretrained models.

Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The growing number of L2 English speakers in India reinforces the need to study accents and L1-L2 interactions. We investigate the accents of Indian English (IE) speakers and report in detail our observations, both specific and common to all regions. In particular, we observe the phonemic variations and phonotactics occurring in the speakers' native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing the native language pronunciations with IE pronunciations obtained jointly from existing literature studies and phonetically annotated speech of 80 speakers. Consequently, we are able to validate the intuitions of Indian language influences on IE pronunciations by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description in terms of universal and region-specific characteristics of IE, which facilitates accent conversion and adaptation of existing ASR and TTS systems to different Indian accents.

The research on text summarization for low-resource Indian languages has been limited due to the availability of relevant datasets. This paper presents a summary of various deep-learning approaches used for the ILSUM 2022 Indic language summarization datasets. The ISUM 2022 dataset consists of news articles written in Indian English, Hindi, and Gujarati respectively, and their ground-truth summarizations. In our work, we explore different pre-trained seq2seq models and fine-tune those with the ILSUM 2022 datasets. In our case, the fine-tuned SoTA PEGASUS model worked the best for English, the fine-tuned IndicBART model with augmented data for Hindi, and again fine-tuned PEGASUS model along with a translation mapping-based approach for Gujarati. Our scores on the obtained inferences were evaluated using ROUGE-1, ROUGE-2, and ROUGE-4 as the evaluation metrics.