{"total":17,"rows":[{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2510.07686","title":"Stress-Testing Model Specs Reveals Character Differences among Language Models","created":"2025-10-09","cited_by_count":13,"area":null},{"id":"2407.02472","title":"ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2505.19030","title":"RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data","created":"2025-05-25","cited_by_count":12,"area":null},{"id":"2407.18421","title":"Self-Directed Synthetic Dialogues and Revisions Technical Report","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2409.18203","title":"Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2605.30803","title":"PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2502.17541","title":"Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2603.24586","title":"Comparing Developer and LLM Biases in Code Evaluation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.29857","title":"Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.07766","title":"Alignment Plausibility: A New Standard for Assuring AI in Healthcare","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.09153","title":"TRACE: TRajectory Attribution for Automated Context Engineering","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.14226","title":"Corpus Characterization and Inverse Constitutional Fine-Tuning for Style-Aware Radiology Reports","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}