{"total":146,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"area":null},{"id":"2406.15981","title":"Serial Position Effects of Large Language Models","created":"2024-06-23","cited_by_count":30,"area":null},{"id":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2210.14712","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2304.00958","title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains","created":"2023-04-03","cited_by_count":27,"area":null},{"id":"2305.16252","title":"Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2310.13206","title":"Primacy Effect of ChatGPT","created":"2023-10-20","cited_by_count":27,"area":null},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26,"area":null},{"id":"2406.02396","title":"The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding","created":"2024-06-04","cited_by_count":26,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2305.07157","title":"Exploring Zero and Few-shot Techniques for Intent Classification","created":"2023-05-11","cited_by_count":21,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2502.11367","title":"Sparse Autoencoder Features for Classifications and Transferability","created":"2025-02-17","cited_by_count":21,"area":"mechinterp"},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20,"area":null},{"id":"2408.03900","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","created":"2024-08-07","cited_by_count":20,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19,"area":null},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2307.14031","title":"Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems","created":"2023-07-26","cited_by_count":16,"area":null},{"id":"2402.13459","title":"Learning to Poison Large Language Models for Downstream Manipulation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2410.00927","title":"Text Clustering as Classification with LLMs","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2206.07808","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","created":"2022-06-15","cited_by_count":15,"area":"distill"},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15,"area":null},{"id":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15,"area":null},{"id":"2307.05410","title":"BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams","created":"2023-07-11","cited_by_count":15,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","cited_by_count":12,"area":null},{"id":"2310.08232","title":"Language Models are Universal Embedders","created":"2023-10-12","cited_by_count":11,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2306.08502","title":"ITALIC: An Italian Intent Classification Dataset","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2410.06707","title":"Calibrating Verbalized Probabilities for Large Language Models","created":"2024-10-09","cited_by_count":10,"area":null},{"id":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2410.24200","title":"Length-Induced Embedding Collapse in PLM-based Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2507.18546","title":"GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface","created":"2025-07-24","cited_by_count":9,"area":null},{"id":"2508.08424","title":"Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2602.07143","title":"Massive Sound Embedding Benchmark (MSEB)","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8,"area":"alignment"},{"id":"2411.10670","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","created":"2024-11-16","cited_by_count":8,"area":null},{"id":"2510.02294","title":"F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data","created":"2025-10-02","cited_by_count":8,"area":null},{"id":"2301.10546","title":"Backward Compatibility During Data Updates by Weight Interpolation","created":"2023-01-25","cited_by_count":7,"area":null},{"id":"2305.16724","title":"Code-Switched Text Synthesis in Unseen Language Pairs","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2412.08587","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2509.08824","title":"Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora","created":"2025-09-10","cited_by_count":7,"area":null},{"id":"2209.12944","title":"On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2310.16609","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2404.10877","title":"Incubating Text Classifiers Following User Instruction with Nothing but LLM","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2508.12459","title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2509.15389","title":"Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2602.05150","title":"GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2501.12332","title":"Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration","created":"2025-01-21","cited_by_count":5,"area":null},{"id":"2505.13136","title":"New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2509.14008","title":"Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2511.17808","title":"PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2602.06205","title":"Multi-Way Representation Alignment","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2304.13292","title":"Zero-Shot Slot and Intent Detection in Low-Resource Languages","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2304.13557","title":"\"I'm\" Lost in Translation: Pronoun Missteps in Crowdsourced Data Sets","created":"2023-04-22","cited_by_count":4,"area":null},{"id":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2305.13528","title":"Transfer-Free Data-Efficient Multilingual Slot Labeling","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2502.09667","title":"Summaries as Centroids for Interpretable and Scalable Text Clustering","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","cited_by_count":4,"area":null},{"id":"2212.06346","title":"The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition","created":"2022-12-13","cited_by_count":3,"area":null},{"id":"2302.09207","title":"RETVec: Resilient and Efficient Text Vectorizer","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2311.12375","title":"The Obscure Limitation of Modular Multilingual Language Models","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2402.04222","title":"What is \"Typological Diversity\" in NLP?","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2403.17599","title":"Coimagining the Future of Voice Assistants with Cultural Sensitivity","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2409.03346","title":"Sketch: A Toolkit for Streamlining LLM Operations","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2504.15640","title":"Cequel: Cost-Effective Querying of Large Language Models for Text Clustering","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2508.21632","title":"QZhou-Embedding Technical Report","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2210.07313","title":"Bootstrapping Multilingual Semantic Parsers using Large Language Models","created":"2022-10-13","cited_by_count":2,"area":"synth"},{"id":"2301.02010","title":"HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2312.04024","title":"k* Distribution: Evaluating the Latent Space of Deep Neural Networks using Local Neighborhood Analysis","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2408.03819","title":"Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2410.18146","title":"Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2501.03870","title":"Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2504.20356","title":"What Causes Knowledge Loss in Multilingual Language Models?","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.03229","title":"Survey of Abstract Meaning Representation: Then, Now, Future","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2510.06747","title":"LLMs Enable Bag-of-Texts Representations for Short-Text Clustering","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2602.12687","title":"Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty","created":"2026-02-13","cited_by_count":2,"area":"distill"},{"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":"2610.02267","title":"Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses","created":"2026-10-01","cited_by_count":2,"area":"agents"},{"id":"2305.10625","title":"Measuring and Mitigating Local Instability in Deep Neural Networks","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2306.07797","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2309.10089","title":"HTEC: Human Transcription Error Correction","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2506.01592","title":"Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.07274","title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","created":"2025-07-09","cited_by_count":1,"area":"mllm"},{"id":"2509.02503","title":"L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages","created":"2025-09-02","cited_by_count":1,"area":null}],"next_cursor":"100"}