{"total":18,"rows":[{"id":"2502.08395","title":"IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2506.08952","title":"Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2509.22367","title":"What Is The Political Content in LLMs' Pre- and Post-Training Data?","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2506.06751","title":"Geopolitical biases in LLMs: what are the \"good\" and the \"bad\" countries according to contemporary language models","created":"2025-06-07","cited_by_count":6,"area":null},{"id":"2508.20015","title":"Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2509.22703","title":"AccessEval: Benchmarking Disability Bias in Large Language Models","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2603.23841","title":"PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2510.12689","title":"From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2508.15855","title":"Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.00963","title":"Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2510.01258","title":"Measuring Algorithmic Partisanship via Zero-Shot Classification and Its Implications on Political Discourse","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.22771","title":"Reducing Political Manipulation with Consistency Training","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.10209","title":"Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.02089","title":"IDEEA: training-free Input-Dependent stEEring via Activation cluster matching","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.15207","title":"Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}