{"total":27,"rows":[{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16,"area":null},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2410.24175","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","created":"2024-10-31","cited_by_count":11,"area":null},{"id":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2603.26680","title":"AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment","created":"2026-03-09","cited_by_count":10,"area":null},{"id":"2412.20984","title":"Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2410.19471","title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2602.07164","title":"Your Language Model Secretly Contains Personality Subnetworks","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2602.17695","title":"EXACT: Explicit Attribute-Guided Decoding-Time Personalization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2506.06715","title":"A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2511.01891","title":"Multi-Personality Generation of LLMs at Decoding-time","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2503.16728","title":"Natural Language Generation","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.15094","title":"Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26853","title":"COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation","created":"2026-09-22","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},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}