{"total":31,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338,"area":null},{"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":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2110.05456","title":"Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation","created":"2021-10-11","cited_by_count":29,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2108.01182","title":"Underreporting of errors in NLG output, and what to do about it","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2202.13756","title":"Data-to-text Generation with Variational Sequential Planning","created":"2022-02-28","cited_by_count":17,"area":null},{"id":"2401.10186","title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation","created":"2024-01-18","cited_by_count":16,"area":null},{"id":"2309.05217","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","created":"2023-09-11","cited_by_count":15,"area":null},{"id":"2108.05644","title":"Generation Challenges: Results of the Accuracy Evaluation Shared Task","created":"2021-08-12","cited_by_count":9,"area":null},{"id":"2204.05879","title":"Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2504.08697","title":"LLMs as Span Annotators: A Comparative Study of LLMs and Humans","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2305.04782","title":"HistAlign: Improving Context Dependency in Language Generation by Aligning with History","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2308.00399","title":"Tackling Hallucinations in Neural Chart Summarization","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2402.15422","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2104.04412","title":"Towards objectively evaluating the quality of generated medical summaries","created":"2021-04-09","cited_by_count":5,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2401.07897","title":"The Pitfalls of Defining Hallucination","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2502.13674","title":"SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2504.19061","title":"Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models","created":"2025-04-27","cited_by_count":4,"area":null},{"id":"2305.06274","title":"Context-Aware Document Simplification","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2404.04103","title":"Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2605.23715","title":"NLG Evaluation: Past, Present, Future","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2206.13435","title":"Comparing informativeness of an NLG chatbot vs graphical app in diet-information domain","created":"2022-06-23","cited_by_count":1,"area":null},{"id":"2404.07836","title":"Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2606.09376","title":"Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2505.11965","title":"CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2607.06495","title":"Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}