{"total":139,"rows":[{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"area":null},{"id":"2403.06350","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","created":"2024-03-11","cited_by_count":52,"area":null},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2401.15006","title":"Airavata: Introducing Hindi Instruction-tuned LLM","created":"2024-01-26","cited_by_count":32,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2407.13522","title":"INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages","created":"2024-07-18","cited_by_count":24,"area":null},{"id":"2407.05841","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","created":"2024-07-08","cited_by_count":20,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2405.20835","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","created":"2024-05-31","cited_by_count":12,"area":null},{"id":"2404.00399","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","created":"2024-03-30","cited_by_count":10,"area":null},{"id":"2405.19462","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2501.14491","title":"Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter","created":"2025-01-24","cited_by_count":10,"area":null},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2401.12097","title":"An Empirical Study of In-context Learning in LLMs for Machine Translation","created":"2024-01-22","cited_by_count":9,"area":null},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2311.09216","title":"Assessing Translation capabilities of Large Language Models involving English and Indian Languages","created":"2023-11-15","cited_by_count":8,"area":null},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2407.14056","title":"Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings","created":"2024-07-19","cited_by_count":7,"area":null},{"id":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2504.10335","title":"MorphTok: Morphologically Grounded Tokenization for Indian Languages","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.03893","title":"How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2502.20420","title":"Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2508.07090","title":"BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2308.03024","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","created":"2023-08-06","cited_by_count":5,"area":null},{"id":"2312.09508","title":"IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2404.08705","title":"Introducing L2M3, A Multilingual Medical Large Language Model to Advance Health Equity in Low-Resource Regions","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2408.00283","title":"Navigating Text-to-Image Generative Bias across Indic Languages","created":"2024-08-01","cited_by_count":5,"area":null},{"id":"2411.04699","title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2412.05710","title":"PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks","created":"2024-12-07","cited_by_count":5,"area":null},{"id":"2412.13860","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2406.09559","title":"Decoding the Diversity: A Review of the Indic AI Research Landscape","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2406.10993","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2505.18609","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2401.14559","title":"Language Modelling Approaches to Adaptive Machine Translation","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2402.04609","title":"Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2404.02512","title":"Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Languages","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2408.09437","title":"Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2408.11382","title":"Towards Inducing Long-Context Abilities in Multilingual Neural Machine Translation Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2502.19074","title":"Improving the quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2503.23088","title":"UNITYAI-GUARD: Pioneering Toxicity Detection Across Low-Resource Indian Languages","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2511.03295","title":"How to Evaluate Speech Translation with Source-Aware Neural MT Metrics","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2407.13435","title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.05401","title":"Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2410.17901","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2505.17102","title":"BanglaByT5: Byte-Level Modelling for Bangla","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.18466","title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2506.03793","title":"Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2601.07314","title":"Mitrasamgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2605.29379","title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2401.15579","title":"MunTTS: A Text-to-Speech System for Mundari","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2402.15967","title":"Direct Punjabi to English speech translation using discrete units","created":"2024-02-25","cited_by_count":1,"area":null},{"id":"2404.19254","title":"Suvach -- Generated Hindi QA benchmark","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2406.13332","title":"How effective is Multi-source pivoting for Translation of Low Resource Indian Languages?","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2409.02712","title":"A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2409.13747","title":"Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2410.17973","title":"Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2411.19096","title":"Pralekha: Cross-Lingual Document Alignment for Indic Languages","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2502.19067","title":"IndicEval-XL: Bridging Linguistic Diversity in Code Generation Across Indic Languages","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2504.07989","title":"Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.21937","title":"Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.19548","title":"Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2509.19941","title":"CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.00270","title":"POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.00486","title":"Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2511.03498","title":"BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2601.05874","title":"Continual-learning for Modelling Low-Resource Languages from Large Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2603.14053","title":"NepTam: A Nepali-Tamang Parallel Corpus and Baseline Machine Translation Experiments","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2603.24307","title":"Samas\\=amayik: A Parallel Dataset for Hindi-Sanskrit Machine Translation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.18423","title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.29489","title":"Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2609.29511","title":"EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2402.07519","title":"MAFIA: Multi-Adapter Fused Inclusive LanguAge Models","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2407.10582","title":"Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2408.11457","title":"Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2409.15879","title":"Machine Translation Advancements of Low-Resource Indian Languages by Transfer Learning","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2410.03215","title":"NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.13443","title":"NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2410.13445","title":"Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2411.00727","title":"SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2411.18368","title":"AMPS: ASR with Multimodal Paraphrase Supervision","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2412.05708","title":"On the effective transfer of knowledge from English to Hindi Wikipedia","created":"2024-12-07","cited_by_count":0,"area":null},{"id":"2412.12997","title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2412.15471","title":"A Review of the Marathi Natural Language Processing","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2412.16894","title":"Unsupervised Bilingual Lexicon Induction for Low Resource Languages","created":"2024-12-22","cited_by_count":0,"area":null},{"id":"2502.05923","title":"ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2504.04155","title":"GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2504.05914","title":"High-Resource Translation:Turning Abundance into Accessibility","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2504.16627","title":"TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval","created":"2025-04-23","cited_by_count":0,"area":null}],"next_cursor":"100"}