{"total":25,"rows":[{"id":"2504.02768","title":"MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs","created":"2025-04-03","cited_by_count":71,"area":null},{"id":"2411.14198","title":"Why do language models perform worse for morphologically complex languages?","created":"2024-11-21","cited_by_count":62,"area":null},{"id":"2505.24689","title":"BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization","created":"2025-05-30","cited_by_count":12,"area":null},{"id":"2506.13487","title":"TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2510.21909","title":"Explaining and Mitigating Crosslingual Tokenizer Inequities","created":"2025-10-24","cited_by_count":7,"area":null},{"id":"2504.03036","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2411.12262","title":"Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2507.03473","title":"Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2601.14051","title":"Kakugo: Distillation of Low-Resource Languages into Small Language Models","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.03551","title":"Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2608.25832","title":"Skill Issue: Are Skills Language-Invariant in LLMs?","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2505.16277","title":"Spontaneous Speech Variables for Evaluating LLMs Cognitive Plausibility","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2601.10310","title":"Multilinguality as Sense Adaptation","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.03508","title":"Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.25846","title":"On the Limits of Model Merging for Multilinguality in Pre-Training","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.08847","title":"Explicit Boundary Markers for Subword Vocabularies","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.12278","title":"Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.15129","title":"Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.27115","title":"Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.09554","title":"BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.37121","title":"Cross-Linguistic Effects in Bilingual Phoneme BabyLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13607","title":"BLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity Items","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16201","title":"L\\\"ushi-1840: Building and Probing a Knowledge Cutoff for a Classical Chinese Language Model","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}