{"total":18,"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":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2107.13935","title":"Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition","created":"2021-07-29","cited_by_count":11,"area":null},{"id":"2211.16259","title":"Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora","created":"2022-11-29","cited_by_count":11,"area":null},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2210.07373","title":"Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2302.09820","title":"Improving User Controlled Table-To-Text Generation Robustness","created":"2023-02-20","cited_by_count":6,"area":null},{"id":"2401.16454","title":"KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants","created":"2024-01-29","cited_by_count":4,"area":null},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2311.08705","title":"Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2408.00675","title":"Leveraging Entailment Judgements in Cross-Lingual Summarisation","created":"2024-08-01","cited_by_count":0,"area":null}],"next_cursor":null}