{"total":16,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2304.07987","title":"Chinese Open Instruction Generalist: A Preliminary Release","created":"2023-04-17","cited_by_count":35,"area":null},{"id":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22,"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":"2305.14150","title":"WYWEB: A NLP Evaluation Benchmark For Classical Chinese","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2402.13109","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2202.07362","title":"MuLD: The Multitask Long Document Benchmark","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2410.09527","title":"LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English","created":"2024-10-12","cited_by_count":8,"area":null},{"id":"2308.14353","title":"ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2405.17732","title":"C$^{3}$Bench: A Comprehensive Classical Chinese Understanding Benchmark for Large Language Models","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2508.15791","title":"InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2512.17756","title":"AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2511.18926","title":"MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems","created":"2025-11-24","cited_by_count":0,"area":null}],"next_cursor":null}