{"total":50,"rows":[{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"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":"2105.01735","title":"HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish","created":"2021-05-04","cited_by_count":51,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2410.18565","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2205.08808","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","created":"2022-05-18","cited_by_count":13,"area":null},{"id":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2305.05486","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2306.07902","title":"Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2203.01215","title":"Mukayese: Turkish NLP Strikes Back","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2212.08897","title":"PolQA: Polish Question Answering Dataset","created":"2022-12-17","cited_by_count":7,"area":null},{"id":"2505.12306","title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2108.01139","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2308.10592","title":"BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","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":"2601.11579","title":"Bielik 11B v3: Multilingual Large Language Model for European Languages","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2505.02550","title":"Bielik v3 Small: Technical Report","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2402.09759","title":"Efficient Language Adaptive Pre-training: Extending State-of-the-Art Large Language Models for Polish","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2204.04937","title":"Assessment of Massively Multilingual Sentiment Classifiers","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2310.14557","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2410.04254","title":"Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia","created":"2024-10-05","cited_by_count":3,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2202.07791","title":"Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2305.05474","title":"Going beyond research datasets: Novel intent discovery in the industry setting","created":"2023-05-09","cited_by_count":2,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2506.07645","title":"Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2506.16322","title":"PL-Guard: Benchmarking Language Model Safety for Polish","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2108.02605","title":"EENLP: Cross-lingual Eastern European NLP Index","created":"2021-08-05","cited_by_count":1,"area":null},{"id":"2108.10580","title":"Detection of Criminal Texts for the Polish State Border Guard","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2308.03103","title":"Improving Domain-Specific Retrieval by NLI Fine-Tuning","created":"2023-08-06","cited_by_count":1,"area":null},{"id":"2404.17832","title":"Evaluation of Few-Shot Learning for Classification Tasks in the Polish Language","created":"2024-04-27","cited_by_count":1,"area":null},{"id":"2412.17533","title":"Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2511.03830","title":"Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.10799","title":"Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","cited_by_count":0,"area":null},{"id":"2307.07007","title":"Electoral Agitation Data Set: The Use Case of the Polish Election","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2406.10255","title":"WarCov -- Large multilabel and multimodal dataset from social platform","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2502.20046","title":"Polish-ASTE: Aspect-Sentiment Triplet Extraction Datasets for Polish","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2601.09722","title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2609.01379","title":"Polish ModernBERT: The Long and Short of Polish Language Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.29266","title":"Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}