{"total":89,"rows":[{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2407.05975","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"area":null},{"id":"2407.19672","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","created":"2024-07-29","cited_by_count":36,"area":null},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2407.12402","title":"TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish","created":"2024-07-17","cited_by_count":32,"area":null},{"id":"2409.15452","title":"CUTE: Measuring LLMs' Understanding of Their Tokens","created":"2024-09-23","cited_by_count":31,"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":"2508.04796","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","created":"2025-08-06","cited_by_count":20,"area":null},{"id":"2410.12656","title":"Evaluating Morphological Compositional Generalization in Large Language Models","created":"2024-10-16","cited_by_count":19,"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":"2408.03837","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2410.00863","title":"On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2411.15462","title":"HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter","created":"2024-11-23","cited_by_count":13,"area":null},{"id":"2406.15741","title":"Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level","created":"2024-06-22","cited_by_count":12,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2505.12584","title":"Improving Multilingual Language Models by Aligning Representations through Steering","created":"2025-05-19","cited_by_count":11,"area":null},{"id":"2408.06273","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","created":"2024-08-12","cited_by_count":10,"area":null},{"id":"2409.12623","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","created":"2024-09-19","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":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"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":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2408.14398","title":"On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2503.00995","title":"Evaluating Polish linguistic and cultural competency in large language models","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2502.12769","title":"How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2410.21573","title":"Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense","created":"2024-10-28","cited_by_count":4,"area":null},{"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":"2502.16682","title":"Automatic Input Rewriting Improves Translation with Large Language Models","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2410.16520","title":"AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2505.00114","title":"Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2408.08848","title":"PsychoLex: Unveiling the Psychological Mind of Large Language Models","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2408.11847","title":"Prompto: An open source library for asynchronous querying of LLM endpoints","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2503.05280","title":"Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2503.07827","title":"Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.12300","title":"HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.17894","title":"Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.04385","title":"MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2509.21820","title":"Can LLMs Generate and Solve Linguistic Olympiad Puzzles?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.07213","title":"Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2511.07498","title":"Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2607.04029","title":"CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2412.16355","title":"Social Science Is Necessary for Operationalizing Socially Responsible Foundation Models","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2501.06286","title":"Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2503.22973","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2506.20793","title":"Multi-lingual Functional Evaluation for Large Language Models","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.07860","title":"Large Language Models for Czech Aspect-Based Sentiment Analysis","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2510.14307","title":"MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2601.17277","title":"PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2606.17234","title":"Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2410.21501","title":"SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2412.12417","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2412.12956","title":"SnakModel: Lessons Learned from Training an Open Danish Large Language Model","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2412.20440","title":"Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2503.10229","title":"R.U.Psycho? Robust Unified Psychometric Testing of Language Models","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2504.21635","title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.16036","title":"OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.18091","title":"Evaluating Prompt-Based and Fine-Tuned Approaches to Czech Anaphora Resolution","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2510.19628","title":"CrossNews-UA: A Cross-lingual News Semantic Similarity Benchmark for Ukrainian, Polish, Russian, and English","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.02858","title":"To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMs","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.03025","title":"LittiChoQA: Literary Texts in Indic Languages Chosen for Question Answering","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.10096","title":"Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.08625","title":"Do Multilingual LLMs have specialized language heads?","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.01224","title":"Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.25420","title":"SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.27481","title":"XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.18960","title":"When Audit Quality Fails to Predict Downstream Utility: A Counterfactual Study of Synthetic-Data Selectors for Low-Resource African NLP","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.31727","title":"The Ongiini-Eval-OW Benchmark: A Concept Paper for the Planned Benchmarking of Machine Translation and Large Language Models on Oshindonga and Oshikwanyama","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.37287","title":"VISTA-Bench: Benchmarking Multilingual Image Translation with Image-Specific Rubrics","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}