{"total":13,"rows":[{"id":"2401.00287","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","created":"2023-12-30","cited_by_count":67,"area":null},{"id":"2311.00306","title":"Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2406.14686","title":"A Contrastive Learning Approach to Mitigate Bias in Speech Models","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2402.14296","title":"Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2507.22720","title":"Investigating Hallucination in Conversations for Low Resource Languages","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2602.00300","title":"Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2504.11431","title":"Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2509.21946","title":"Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2512.19735","title":"Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Prompting","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":null}