arXiv subjects

Maharaj Brahma

Publications and source records attributed to Maharaj Brahma.

6 recordsLinked to original sources

arXiv2026

Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations

Large Language Models (LLMs) demonstrate strong multilingual reasoning performance, yet their robustness to semantics-preserving structural variation remains underexplored, particularly for relatively free word-order languages. We investigate the structural sensitivity of multilingual LLMs using two linguistically grounded perturbation settings in Hindi and Malayalam: constrained constituent reordering and active-passive voice transformation. We introduce a benchmark dataset IndicReStruct, with two variants, GSM8K-Reordered and GSM8K-Voice, constructed from GSM8K while preserving semantic meaning. Across six state-of-the-art LLMs and multiple prompting strategies, we observe consistent and significant degradation in mathematical reasoning performance under structurally perturbed inputs. To further understand these failures, we perform qualitative error analysis and mechanistic interpretability experiments using residual-stream activation patching. Our analyses show that reasoning failures frequently arise from disruptions in entity-quantity alignment and that intermediate transformer layers contribute most strongly toward reasoning restoration. Overall, our findings suggest that current multilingual LLMs remain highly sensitive to surface syntactic realization and lack robust compositional invariance under structurally different but semantically equivalent inputs.

cs.CL↗

arXiv2026

Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights

Tokenization plays a pivotal role in NLP and is fundamental to training language models. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those in the Indian subcontinent. In this work, we present a comprehensive empirical study of multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families. We systematically evaluate the effects of (i) widely used subword algorithms: BPE and Unigram LM, (ii) script and orthography-aware normalization, (iii) vocabulary size, and (iv) multilingual vocabulary construction strategies. We use a combination of intrinsic and extrinsic evaluations to obtain the following observations: (i) script-specific normalization improves tokenization quality, (ii) Unigram LM better preserves morphological boundaries than BPE, (iii) cluster-based vocabulary construction shows improvement in downstream tasks compared to the joint method. Our findings highlight the importance of linguistically informed design choices in multilingual tokenization and offer practical guidance for building effective tokenizers for low-resource and morphologically complex languages.

cs.CL↗

arXiv2025

DIWALI: Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

Large language models (LLMs) are widely used in various tasks and applications. However, despite their wide capabilities, they are shown to lack cultural alignment \citep{ryan-etal-2024-unintended, alkhamissi-etal-2024-investigating} and produce biased generations \cite{naous-etal-2024-beer} due to a lack of cultural knowledge and competence. Evaluation of LLMs for cultural awareness and alignment is particularly challenging due to the lack of proper evaluation metrics and unavailability of culturally grounded datasets representing the vast complexity of cultures at the regional and sub-regional levels. Existing datasets for culture specific items (CSIs) focus primarily on concepts at the regional level and may contain false positives. To address this issue, we introduce a novel CSI dataset for Indian culture, belonging to 17 cultural facets. The dataset comprises ~8k cultural concepts from 36 sub-regions. To measure the cultural competence of LLMs on a cultural text adaptation task, we evaluate the adaptations using the CSIs created, LLM as Judge, and human evaluations from diverse socio-demographic region. Furthermore, we perform quantitative analysis demonstrating selective sub-regional coverage and surface-level adaptations across all considered LLMs. Our dataset is available here: https://huggingface.co/datasets/nlip/DIWALI, project webpage https://nlip-lab.github.io/nlip/publications/diwali/, and our codebase with model outputs can be found here: https://github.com/pramitsahoo/culture-evaluation

cs.CL↗

arXiv2025

MorphTok: Morphologically Grounded Tokenization for Indian Languages

Tokenization is a crucial step in NLP, especially with the rise of large language models (LLMs), impacting downstream performance, computational cost, and efficiency. Existing LLMs rely on the classical Byte-pair Encoding (BPE) algorithm for subword tokenization that greedily merges frequent character bigrams, often leading to segmentation that does not align with linguistically meaningful units. To address this, we propose morphology-aware segmentation as a pre-tokenization step before applying BPE. To facilitate morphology-aware segmentation, we create a novel dataset for Hindi and Marathi, incorporating sandhi splitting to enhance the subword tokenization. Experiments on downstream tasks show that morphologically grounded tokenization improves machine translation and language modeling performance. Additionally, to handle the dependent vowels common in syllable-based writing systems used by Indic languages, we propose Constrained BPE (CBPE), an extension to the standard BPE algorithm incorporating script-specific constraints. In particular, CBPE handles dependent vowels to form a cohesive unit with other characters instead of occurring as a single unit. Our results show that CBPE achieves a 1.68\% reduction in fertility scores while maintaining comparable or improved downstream performance in machine translation and language modeling, offering a computationally efficient alternative to standard BPE. Moreover, to evaluate segmentation across different tokenization algorithms, we introduce a new human evaluation metric, \textit{EvalTok}, enabling more human-grounded assessment.

cs.CL↗

arXiv2024

NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task

This paper describes NLIP Lab's multilingual machine translation system for the WAT24 shared task on multilingual Indic MT task for 22 scheduled languages belonging to 4 language families. We explore pre-training for Indic languages using alignment agreement objectives. We utilize bi-lingual dictionaries to substitute words from source sentences. Furthermore, we fine-tuned language direction-specific multilingual translation models using small and high-quality seed data. Our primary submission is a 243M parameters multilingual translation model covering 22 Indic languages. In the IN22-Gen benchmark, we achieved an average chrF++ score of 46.80 and 18.19 BLEU score for the En-Indic direction. In the Indic-En direction, we achieved an average chrF++ score of 56.34 and 30.82 BLEU score. In the In22-Conv benchmark, we achieved an average chrF++ score of 43.43 and BLEU score of 16.58 in the En-Indic direction, and in the Indic-En direction, we achieved an average of 52.44 and 29.77 for chrF++ and BLEU respectively. Our model\footnote{Our code and models are available at \url{https://github.com/maharajbrahma/WAT2024-MultiIndicMT}} is competitive with IndicTransv1 (474M parameter model).

cs.CL↗

arXiv2024

NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task

In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng $\leftrightarrow$ {as, kha, lus, mni} as participating language pairs. In this shared task, we explore the finetuning of a pre-trained model motivated by the pre-trained objective of aligning embeddings closer by alignment augmentation \cite{lin-etal-2020-pre} for 22 scheduled Indian languages. Our primary system is based on language-specific finetuning on a pre-trained model. We achieve chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for eng$\rightarrow$as, eng$\rightarrow$kha, eng$\rightarrow$lus, eng$\rightarrow$mni respectively. We also explore multilingual training with/without language grouping and layer-freezing. Our code, models, and generated translations are available here: https://github.com/pramitsahoo/WMT2024-LRILT.

cs.CL↗