{"total":46,"rows":[{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43,"area":null},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33,"area":null},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"area":null},{"id":"2402.11161","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28,"area":null},{"id":"2402.02056","title":"AnthroScore: A Computational Linguistic Measure of Anthropomorphism","created":"2024-02-03","cited_by_count":27,"area":null},{"id":"2405.06563","title":"What Can Natural Language Processing Do for Peer Review?","created":"2024-05-10","cited_by_count":25,"area":null},{"id":"2304.14238","title":"The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2306.09562","title":"Reproducibility in NLP: What Have We Learned from the Checklist?","created":"2023-06-16","cited_by_count":18,"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":"2404.12691","title":"Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?","created":"2024-04-19","cited_by_count":15,"area":null},{"id":"2303.16166","title":"When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP","created":"2023-03-28","cited_by_count":14,"area":null},{"id":"2308.07832","title":"REFORMS: Reporting Standards for Machine Learning Based Science","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2311.18807","title":"Pre-registration for Predictive Modeling","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2201.11443","title":"Yes-Yes-Yes: Proactive Data Collection for ACL Rolling Review and Beyond","created":"2022-01-27","cited_by_count":12,"area":null},{"id":"2204.05042","title":"Resources for Turkish Natural Language Processing: A critical survey","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2402.06353","title":"Copycats: the many lives of a publicly available medical imaging dataset","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2505.17362","title":"A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2305.16579","title":"NLP Reproducibility For All: Understanding Experiences of Beginners","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2406.10085","title":"Enhancing Question Answering on Charts Through Effective Pre-training Tasks","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2410.12691","title":"Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2304.08315","title":"Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2309.11691","title":"RAI4IoE: Responsible AI for Enabling the Internet of Energy","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2111.02034","title":"Building Legal Datasets","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2203.03399","title":"Building and curating conversational corpora for diversity-aware language science and technology","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2506.06808","title":"Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2211.12424","title":"One Venue, Two Conferences: The Separation of Chinese and American Citation Networks","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2404.14740","title":"Modeling the Sacred: Considerations when Using Religious Texts in Natural Language Processing","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2408.04675","title":"ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2410.03545","title":"Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2605.20793","title":"Assessing socio-economic climate impacts from text data","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.07936","title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2211.05604","title":"An Inclusive Notion of Text","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2401.13170","title":"CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2406.19543","title":"Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2410.03676","title":"A quest through interconnected datasets: lessons from highly-cited ICASSP papers","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2605.13801","title":"Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.30107","title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.21869","title":"The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.02416","title":"The Future of NLP may not be at NLP Conferences: Scholarly Migration Patterns in Natural Language Processing","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.09280","title":"Is the ACL Responsible NLP Checklist a Box-Ticking Exercise? A Large-Scale Analysis of EMNLP 2025","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.30866","title":"Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}