{"total":18,"rows":[{"id":"2305.15004","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","created":"2023-05-24","cited_by_count":45,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2402.10712","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","created":"2024-02-16","cited_by_count":18,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2601.21708","title":"FBS: Modeling Native Parallel Reading inside a Transformer","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2403.15747","title":"CodeShell Technical Report","created":"2024-03-23","cited_by_count":6,"area":null},{"id":"2406.06366","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2501.02432","title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2506.11903","title":"GeistBERT: Breathing Life into German NLP","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2510.21364","title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2311.12537","title":"Oasis: Data Curation and Assessment System for Pretraining of Large Language Models","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2509.09990","title":"CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2606.02100","title":"PortBERT: Navigating the Depths of Portuguese Language Models","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2410.08800","title":"Data Processing for the OpenGPT-X Model Family","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2502.10852","title":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","created":"2025-02-15","cited_by_count":0,"area":null}],"next_cursor":null}