{"total":15,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"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":"2205.14036","title":"StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2405.12744","title":"The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.03884","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2310.12936","title":"A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2410.17739","title":"Local Contrastive Editing of Gender Stereotypes","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2404.05866","title":"GeniL: A Multilingual Dataset on Generalizing Language","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2601.04393","title":"Assessing the quality and coherence of word embeddings after SCM-based intersectional bias mitigation","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2501.15351","title":"Fairness in LLM-Generated Surveys","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2503.01947","title":"Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts","created":"2025-03-03","cited_by_count":1,"area":null}],"next_cursor":null}