{"total":53,"rows":[{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58,"area":null},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"area":null},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30,"area":null},{"id":"2603.11510","title":"Tiny Aya: Bridging Scale and Multilingual Depth","created":"2026-03-12","cited_by_count":15,"area":null},{"id":"2412.04193","title":"AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2504.12104","title":"Logits DeConfusion with CLIP for Few-Shot Learning","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2506.22724","title":"The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure","created":"2025-06-28","cited_by_count":10,"area":null},{"id":"2510.19546","title":"Conditions for Catastrophic Forgetting in Multilingual Translation","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2409.07054","title":"Native vs Non-Native Language Prompting: A Comparative Analysis","created":"2024-09-11","cited_by_count":9,"area":null},{"id":"2412.10893","title":"BgGPT 1.0: Extending English-centric LLMs to other languages","created":"2024-12-14","cited_by_count":8,"area":null},{"id":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2410.13237","title":"Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2502.02289","title":"Evalita-LLM: Benchmarking Large Language Models on Italian","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2410.15308","title":"LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2504.16677","title":"A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics","created":"2025-04-23","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":"2410.18836","title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2410.23956","title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language","created":"2024-10-31","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":"2503.01150","title":"MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.24102","title":"Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?","created":"2025-03-31","cited_by_count":5,"area":null},{"id":"2510.07037","title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","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":"2602.11174","title":"The Script Tax: Measuring Tokenization-Driven Efficiency and Latency Disparities in Multilingual Language Models","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2505.19116","title":"Controlling Language Confusion in Multilingual LLMs","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2505.06004","title":"Exploring the Feasibility of Multilingual Grammatical Error Correction with a Single LLM up to 9B parameters: A Comparative Study of 17 Models","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2505.14297","title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.05686","title":"Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs","created":"2025-07-08","cited_by_count":2,"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":"2507.03162","title":"MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2509.20557","title":"SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.16690","title":"AI Text Detectors and the Misclassification of Slightly Polished Arabic Text","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2601.00263","title":"Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2602.16290","title":"Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generation","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.27649","title":"Disentangling Language Roles in Multilingual LLM Task Execution","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.12334","title":"Steering the Language Axis: From Linear Decodability to Causal Control","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2410.18040","title":"Key Algorithms for Keyphrase Generation: Instruction-Based LLMs for Russian Scientific Keyphrases","created":"2024-10-23","cited_by_count":0,"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":"2601.02906","title":"Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.12549","title":"Benchmarking Concept-Spilling Across Languages in LLMs","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.16217","title":"ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2603.21047","title":"When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.26553","title":"TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models","created":"2026-04-29","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":"2606.08994","title":"Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.18033","title":"When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.22361","title":"First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.00325","title":"Latent Mechanisms of Language Control in Multilingual Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00958","title":"PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13611","title":"In the Blind: Building Pseudo-References for MT Evaluation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.01674","title":"Invent a Dataset: Measuring dataset generation abilities with zero seed","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}