INDIC DIALECT: A Multi Task Benchmark to Evaluate and Translate in Indian Language Dialects

Recent NLP advances focus primarily on standardized languages, leaving most low-resource dialects under-served especially in Indian scenarios. In India, the issue is particularly important: despite Hindi being the third most spoken language globally (over 600 million speakers), its numerous dialects remain underrepresented. The situation is similar for Odia, which has around 45 million speakers. While some datasets exist which contain standard Hindi and Odia languages, their regional dialects have almost no web presence. We introduce INDIC-DIALECT, a human-curated parallel corpus of 13k sentence pairs spanning 11 dialects and 2 languages: Hindi and Odia. Using this corpus, we construct a multi-task benchmark with three tasks: dialect classification, multiple-choice question (MCQ) answering, and machine translation (MT). Our experiments show that LLMs like GPT-4o and Gemini 2.5 perform poorly on the classification task. While fine-tuned transformer based models pretrained on Indian languages substantially improve performance e.g., improving F1 from 19.6\% to 89.8\% on dialect classification. For dialect to language translation, we find that hybrid AI model achieves highest BLEU score of 61.32 compared to the baseline score of 23.36. Interestingly, due to complexity in generating dialect sentences, we observe that for language to dialect translation the ``rule-based followed by AI" approach achieves best BLEU score of 48.44 compared to the baseline score of 27.59. INDIC-DIALECT thus is a new benchmark for dialect-aware Indic NLP, and we plan to release it as open source to support further work on low-resource Indian dialects.

Get away with less: Need of source side data curation to build parallel corpus for low resource Machine Translation

Data curation is a critical yet under-researched step in the machine translation training paradigm. To train translation systems, data acquisition relies primarily on human translations and digital parallel sources or, to a limited degree, synthetic generation. But, for low-resource languages, human translation to generate sufficient data is prohibitively expensive. Therefore, it is crucial to develop a framework that screens source sentences to form efficient parallel text, ensuring optimal MT system performance in low-resource environments. We approach this by evaluating English-Hindi bi-text to determine effective sentence selection strategies for optimal MT system training. Our extensively tested framework, (Lexical And Linguistically Informed Text Analysis) LALITA, targets source sentence selection using lexical and linguistic features to curate parallel corpora. We find that by training mostly on complex sentences from both existing and synthetic datasets, our method significantly improves translation quality. We test this by simulating low-resource data availabilty with curated datasets of 50K to 800K English sentences and report improved performances on all data sizes. LALITA demonstrates remarkable efficiency, reducing data needs by more than half across multiple languages (Hindi, Odia, Nepali, Norwegian Nynorsk, and German). This approach not only reduces MT systems training cost by reducing training data requirement, but also showcases LALITA's utility in data augmentation.

A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality

Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived from individual words alone. These expressions encode rich, cultural meaning, and have both figurative and literal meanings, making accurate translation difficult. Because models are fairly good at translating compositional text, we investigate GRPO-style fine-tuning using Machine Translation Quality Estimation (MTQE) models as reward functions to train models to better translate idioms. Using Chinese and Hindi idiom datasets, we find that idiom translation abilities improve by ~14 points, general, non-idiomatic translation implicitly improves by ~8 points, and cross-lingual translation abilities (trained on one language, evaluated on another) improves by ~6 points. Overall, our work quantifies the non-compositional translation gap and offers insights for developing LLMs with stronger cross-cultural and figurative language understanding.

Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs

As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily focused on monolingual settings, typically English, multilingual environments introduce additional complexities due to cross-lingual knowledge transfer and biases embedded in both pretraining and fine-tuning data. In this work, we study multilingual unlearning using the Aya-Expanse 8B model under two settings: (1) data unlearning and (2) concept unlearning. We extend benchmarks for factual knowledge and stereotypes to ten languages through translation: English, French, Arabic, Japanese, Russian, Farsi, Korean, Hindi, Hebrew, and Indonesian. These languages span five language families and a wide range of resource levels. Our experiments show that unlearning in high-resource languages is generally more stable, with asymmetric transfer effects observed between typologically related languages. Furthermore, our analysis of linguistic distances indicates that syntactic similarity is the strongest predictor of cross-lingual unlearning behavior.

From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation

In multilingual nations like India, access to legal information is often hindered by language barriers, as much of the legal and judicial documentation remains in English. Legal Machine Translation (L-MT) offers a scalable solution to this challenge by enabling accurate and accessible translations of legal documents. This paper presents our work for the JUST-NLP 2025 Legal MT shared task, focusing on English-Hindi translation using Transformer-based approaches. We experiment with 2 complementary strategies, fine-tuning a pre-trained OPUS-MT model for domain-specific adaptation and training a Transformer model from scratch using the provided legal corpus. Performance is evaluated using standard MT metrics, including SacreBLEU, chrF++, TER, ROUGE, BERTScore, METEOR, and COMET. Our fine-tuned OPUS-MT model achieves a SacreBLEU score of 46.03, significantly outperforming both baseline and from-scratch models. The results highlight the effectiveness of domain adaptation in enhancing translation quality and demonstrate the potential of L-MT systems to improve access to justice and legal transparency in multilingual contexts.

A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation

In this paper, we describe our system under the team name BLEU Monday for the English-to-Indic Multimodal Translation Task at WAT 2025. We participate in the text-only translation tasks for English-Hindi, English-Bengali, English-Malayalam, and English-Odia language pairs. We present a two-stage approach that addresses quality issues in the training data through automated error detection and correction, followed by parameter-efficient model fine-tuning. Our methodology introduces a vision-augmented judge-corrector pipeline that leverages multimodal language models to systematically identify and correct translation errors in the training data. The judge component classifies translations into three categories: correct, visually ambiguous (requiring image context), or mistranslated (poor translation quality). Identified errors are routed to specialized correctors: GPT-4o-mini regenerates captions requiring visual disambiguation, while IndicTrans2 retranslates cases with pure translation quality issues. This automated pipeline processes 28,928 training examples across four languages, correcting an average of 17.1% of captions per language. We then apply Low-Rank Adaptation (LoRA) to fine-tune the IndicTrans2 en-indic 200M distilled model on both original and corrected datasets. Training on corrected data yields consistent improvements, with BLEU score gains of +1.30 for English-Bengali on the evaluation set (42.00 -> 43.30) and +0.70 on the challenge set (44.90 -> 45.60), +0.60 for English-Odia on the evaluation set (41.00 -> 41.60), and +0.10 for English-Hindi on the challenge set (53.90 -> 54.00).

Segmentation Beyond Defaults: Asymmetrical Byte Pair Encoding for Optimal Machine Translation Performance

Existing Machine Translation (MT) research often suggests a single, fixed set of hyperparameters for word segmentation models, symmetric Byte Pair Encoding (BPE), which applies the same number of merge operations (NMO) to train tokenizers for both source and target languages. However, we demonstrate that this uniform approach doesn't guarantee optimal MT performance across different language pairs and data sizes. This work investigates BPE segmentation recipes across various data volumes and language pairs to evaluate MT system performance. We find that utilizing asymmetric BPE, where the source and target languages have different NMOs, significantly improves results over the symmetric approach, especially in low-resource settings (50K, 100K, and 500K sentence pairs). Specifically, asymmetric BPE yield statistically significant ($p<0.05$) average gains of 5.32, 4.46, and 0.7 CHRF++ on English-Hindi in low-resource setups. We validated this trend across six additional language pairs (English and Telugu, Shona, Norwegian, Kyrgyz, Hausa, and Inuktitut), observing statistically significant improvement in 10 out of 12 systems compared to symmetric BPE. Our findings indicate a high NMO for the source (4K to 32K) and a low NMO for the target (0.5K to 2K) provides optimal results, particularly benefiting low-resource MT.

Evaluating Machine Translation Models for English-Hindi Language Pairs: A Comparative Analysis

Machine translation has become a critical tool in bridging linguistic gaps, especially between languages as diverse as English and Hindi. This paper comprehensively evaluates various machine translation models for translating between English and Hindi. We assess the performance of these models using a diverse set of automatic evaluation metrics, both lexical and machine learning-based metrics. Our evaluation leverages an 18000+ corpus of English Hindi parallel dataset and a custom FAQ dataset comprising questions from government websites. The study aims to provide insights into the effectiveness of different machine translation approaches in handling both general and specialized language domains. Results indicate varying performance levels across different metrics, highlighting strengths and areas for improvement in current translation systems.

Pivot Language for Low-Resource Machine Translation

Certain pairs of languages suffer from lack of a parallel corpus which is large in size and diverse in domain. One of the ways this is overcome is via use of a pivot language. In this paper we use Hindi as a pivot language to translate Nepali into English. We describe what makes Hindi a good candidate for the pivot. We discuss ways in which a pivot language can be used, and use two such approaches - the Transfer Method (fully supervised) and Backtranslation (semi-supervised) - to translate Nepali into English. Using the former, we are able to achieve a devtest Set SacreBLEU score of 14.2, which improves the baseline fully supervised score reported by (Guzman et al., 2019) by 6.6 points. While we are slightly below the semi-supervised baseline score of 15.1, we discuss what may have caused this under-performance, and suggest scope for future work.

A Culturally-diverse Multilingual Multimodal Video Benchmark & Model

Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the English language for cultural and linguistic inclusivity is yet to be investigated in the context of video LMMs. In pursuit of more inclusive video LMMs, we introduce a multilingual Video LMM benchmark, named ViMUL-Bench, to evaluate Video LMMs across 14 languages, including both low- and high-resource languages: English, Chinese, Spanish, French, German, Hindi, Arabic, Russian, Bengali, Urdu, Sinhala, Tamil, Swedish, and Japanese. Our ViMUL-Bench is designed to rigorously test video LMMs across 15 categories including eight culturally diverse categories, ranging from lifestyles and festivals to foods and rituals and from local landmarks to prominent cultural personalities. ViMUL-Bench comprises both open-ended (short and long-form) and multiple-choice questions spanning various video durations (short, medium, and long) with 8k samples that are manually verified by native language speakers. In addition, we also introduce a machine translated multilingual video training set comprising 1.2 million samples and develop a simple multilingual video LMM, named ViMUL, that is shown to provide a better tradeoff between high-and low-resource languages for video understanding. We hope our ViMUL-Bench and multilingual video LMM along with a large-scale multilingual video training set will help ease future research in developing cultural and linguistic inclusive multilingual video LMMs. Our proposed benchmark, video LMM and training data will be publicly released at https://mbzuai-oryx.github.io/ViMUL/.