{"total":19,"rows":[{"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":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42,"area":null},{"id":"2304.14072","title":"Origin Tracing and Detecting of LLMs","created":"2023-04-27","cited_by_count":40,"area":null},{"id":"2203.09313","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","created":"2022-03-17","cited_by_count":31,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"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":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"area":null},{"id":"2204.09438","title":"A Corpus for Understanding and Generating Moral Stories","created":"2022-04-20","cited_by_count":16,"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":"2210.10618","title":"Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2307.08074","title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","created":"2023-07-16","cited_by_count":10,"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":"2212.10754","title":"CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2305.08152","title":"STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation","created":"2023-05-14","cited_by_count":5,"area":null},{"id":"2406.04578","title":"SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer","created":"2024-06-07","cited_by_count":4,"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":"2209.08524","title":"A Benchmark for Understanding and Generating Dialogue between Characters in Stories","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2305.09520","title":"DLUE: Benchmarking Document Language Understanding","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2306.02334","title":"Long Text Generation Challenge","created":"2023-06-04","cited_by_count":0,"area":null}],"next_cursor":null}