{"total":23,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2604.03976","title":"Quantifying Trust: Financial Risk Management for Trustworthy AI Agents","created":"2026-04-05","cited_by_count":8,"area":null},{"id":"2410.06415","title":"Biased AI can Influence Political Decision-Making","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2503.15904","title":"More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2504.01420","title":"FAIRE: Assessing Racial and Gender Bias in AI-Driven Resume Evaluations","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2504.03520","title":"Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2505.11189","title":"Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2506.18116","title":"Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives","created":"2025-06-22","cited_by_count":3,"area":null},{"id":"2411.08135","title":"On the Role of Speech Data in Reducing Toxicity Detection Bias","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2505.15475","title":"LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2410.19775","title":"Gender Bias of LLM in Economics: An Existentialism Perspective","created":"2024-10-14","cited_by_count":1,"area":null},{"id":"2503.00619","title":"PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2504.01951","title":"The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2508.17825","title":"FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2410.08388","title":"Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2502.07186","title":"PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2506.22372","title":"Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2508.09651","title":"A Close Reading Approach to Gender Narrative Biases in AI-Generated Stories","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2606.15914","title":"Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.26062","title":"Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities","created":"2026-06-16","cited_by_count":0,"area":null}],"next_cursor":null}