{"total":32,"rows":[{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141,"area":null},{"id":"2210.15230","title":"How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79,"area":null},{"id":"2310.16523","title":"Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2402.15481","title":"Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency","created":"2024-02-23","cited_by_count":15,"area":null},{"id":"2407.15286","title":"Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2310.13915","title":"Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research","created":"2023-10-21","cited_by_count":14,"area":null},{"id":"2407.15184","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","created":"2024-07-21","cited_by_count":11,"area":null},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2504.15941","title":"FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity","created":"2025-04-22","cited_by_count":5,"area":null},{"id":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2305.16357","title":"EDM3: Event Detection as Multi-task Text Generation","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2501.18642","title":"DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2507.00985","title":"Discourse Heuristics For Paradoxically Moral Self-Correction","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2410.20513","title":"Self-correction is Not An Innate Capability in Language Models","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2505.18466","title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2407.16266","title":"Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words","created":"2024-07-23","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":"2107.10295","title":"A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks","created":"2021-07-21","cited_by_count":0,"area":null},{"id":"2304.06031","title":"Fairness: from the ethical principle to the practice of Machine Learning development as an ongoing agreement with stakeholders","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2402.10899","title":"Taxonomy-based CheckList for Large Language Model Evaluation","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2509.23805","title":"Open-DeBias: Toward Mitigating Open-Set Bias in Language Models","created":"2025-09-28","cited_by_count":0,"area":null}],"next_cursor":null}