{"total":21,"rows":[{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"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":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","cited_by_count":11,"area":null},{"id":"2406.03827","title":"Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2308.11284","title":"LEAP: Efficient and Automated Test Method for NLP Software","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2204.09852","title":"The Risks of Machine Learning Systems","created":"2022-04-21","cited_by_count":5,"area":null},{"id":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2109.13037","title":"Language Invariant Properties in Natural Language Processing","created":"2021-09-27","cited_by_count":3,"area":null},{"id":"2505.03563","title":"Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2408.11860","title":"Risks and NLP Design: A Case Study on Procedural Document QA","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2211.11982","title":"BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems","created":"2022-11-22","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":"2410.23186","title":"Reliability of Topic Modeling","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2501.08276","title":"Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2211.15916","title":"BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2304.11223","title":"A Group-Specific Approach to NLP for Hate Speech Detection","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2503.05102","title":"AutoTestForge: A Multidimensional Automated Testing Framework for Natural Language Processing Models","created":"2025-03-07","cited_by_count":0,"area":null}],"next_cursor":null}