{"total":56,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"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":"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":"2410.13394","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2506.15355","title":"SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture","created":"2025-06-18","cited_by_count":16,"area":null},{"id":"2411.12240","title":"Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages","created":"2024-11-19","cited_by_count":11,"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":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2412.00948","title":"Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2412.10244","title":"Efficient Continual Pre-training of LLMs for Low-resource Languages","created":"2024-12-13","cited_by_count":8,"area":null},{"id":"2503.12051","title":"TLUE: A Tibetan Language Understanding Evaluation Benchmark","created":"2025-03-15","cited_by_count":6,"area":null},{"id":"2506.16502","title":"Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples","created":"2025-06-19","cited_by_count":6,"area":"alignment"},{"id":"2407.04459","title":"Generalists vs. Specialists: Evaluating Large Language Models for Urdu","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2407.16160","title":"UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models","created":"2024-07-23","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":"2503.01150","title":"MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.04360","title":"Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2504.16921","title":"IberBench: LLM Evaluation on Iberian Languages","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2512.10780","title":"Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting","created":"2025-12-11","cited_by_count":5,"area":null},{"id":"2602.16832","title":"IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages","created":"2026-02-18","cited_by_count":5,"area":"alignment"},{"id":"2412.04003","title":"Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement","created":"2024-12-05","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":"2508.15876","title":"DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking","created":"2025-08-21","cited_by_count":3,"area":"agents"},{"id":"2508.16185","title":"ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2512.00333","title":"IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2502.17253","title":"MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2506.15372","title":"COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2508.19831","title":"Benchmarking Hindi LLMs: A New Suite of Datasets and a Comparative Analysis","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2511.00960","title":"The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian Riddles","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2604.04532","title":"Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2406.18880","title":"SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2504.20022","title":"Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2507.19699","title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","created":"2025-07-25","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":"2604.02135","title":"GaelEval: Benchmarking LLM Performance for Scottish Gaelic","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.13686","title":"IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2507.01853","title":"Eka-Eval: An Evaluation Framework for Low-Resource Multilingual Large Language Models","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.20718","title":"Uncertainty-driven Embedding Convolution","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.13526","title":"MATA: Mindful Assessment of the Telugu Abilities of Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2510.18344","title":"Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.15183","title":"HinTel-AlignBench: A Framework and Benchmark for Hindi-Telugu with English-Aligned Samples","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.04387","title":"The Language of Bargaining: Linguistic Effects in LLM Negotiations","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2604.18914","title":"MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.27050","title":"BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.31512","title":"Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.03494","title":"Beyond Initialization Loss: A Systematic Study of Token Embedding Initialization Strategies for LLM Vocabulary Extension","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.13722","title":"BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.15535","title":"L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.18117","title":"Position: AI Leaderboards Are Underserving the Global South: A Case Study from India","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2609.01788","title":"VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.12960","title":"Fewer Words, Not Fewer Tokens: Measuring the Sanskrit Tokenization Penalty per Proposition","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.15373","title":"In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}