{"total":30,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2305.13862","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","created":"2023-05-23","cited_by_count":32,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2405.02743","title":"Beyond Performance: Quantifying and Mitigating Label Bias in LLMs","created":"2024-05-04","cited_by_count":25,"area":null},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2212.10755","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","created":"2022-12-21","cited_by_count":11,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2406.17385","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2503.04372","title":"Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms","created":"2025-03-06","cited_by_count":5,"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":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2403.11896","title":"Investigating Markers and Drivers of Gender Bias in Machine Translations","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2403.17553","title":"RuBia: A Russian Language Bias Detection Dataset","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2503.06792","title":"On the Mutual Influence of Gender and Occupation in LLM Representations","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2506.03867","title":"EuroGEST: Investigating gender stereotypes in multilingual language models","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2505.23914","title":"Probing Association Biases in LLM Moderation Over-Sensitivity","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2507.02088","title":"McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2405.02010","title":"The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2211.14639","title":"Gender Biases Unexpectedly Fluctuate in the Pre-training Stage of Masked Language Models","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2305.12620","title":"Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2311.08472","title":"Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2404.11726","title":"Investigating Gender Bias in Turkish Language Models","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2506.01709","title":"Fairness Dynamics During Training","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.01715","title":"Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2606.24596","title":"To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.20779","title":"Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21490","title":"Benchmarking Gender Bias in Machine Translation Evaluation Metrics across Occupations","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}