{"total":23,"rows":[{"id":"2506.17368","title":"SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification","created":"2025-06-20","cited_by_count":18,"area":"alignment"},{"id":"2403.01197","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","created":"2024-03-02","cited_by_count":15,"area":"alignment"},{"id":"2411.17792","title":"H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs","created":"2024-11-26","cited_by_count":11,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2510.02833","title":"Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs","created":"2025-10-03","cited_by_count":10,"area":"alignment"},{"id":"2505.06079","title":"TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations","created":"2025-05-09","cited_by_count":7,"area":"alignment"},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2407.04181","title":"Orchestrating LLMs with Different Personalizations","created":"2024-07-04","cited_by_count":4,"area":"alignment"},{"id":"2605.29708","title":"RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs","created":"2026-05-28","cited_by_count":4,"area":"alignment"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"},{"id":"2511.03939","title":"RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods","created":"2025-11-06","cited_by_count":2,"area":"alignment"},{"id":"2606.04284","title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.21906","title":"Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding","created":"2026-06-20","cited_by_count":2,"area":"alignment"},{"id":"2407.17546","title":"Exploring Domain Robust Lightweight Reward Models based on Router Mechanism","created":"2024-07-24","cited_by_count":1,"area":"alignment"},{"id":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2511.21101","title":"Mortgage Language Model: Domain-Adaptive Pretraining with Residual Instruction, Alignment Tuning, and Task-Specific Routing","created":"2025-11-26","cited_by_count":1,"area":"alignment"},{"id":"1809.01036","title":"A Roadmap for Robust End-to-End Alignment","created":"2018-09-04","cited_by_count":0,"area":"alignment"},{"id":"2512.00724","title":"UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking","created":"2025-11-30","cited_by_count":0,"area":"alignment"},{"id":"2603.16410","title":"PlotTwist: A Creative Plot Generation Framework with Small Language Models","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2603.29259","title":"Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE","created":"2026-03-31","cited_by_count":0,"area":"alignment"},{"id":"2606.08032","title":"Variational Proximal Policy Optimization","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2608.21278","title":"CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment","created":"2026-08-21","cited_by_count":0,"area":"alignment"},{"id":"2609.09793","title":"How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE","created":"2026-09-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}