{"total":14,"rows":[{"id":"2402.09154","title":"Attacking Large Language Models with Projected Gradient Descent","created":"2024-02-14","cited_by_count":94,"area":"alignment"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2305.06176","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","created":"2023-05-09","cited_by_count":8,"area":"alignment"},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7,"area":"alignment"},{"id":"2104.04748","title":"Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management","created":"2021-04-10","cited_by_count":6,"area":"alignment"},{"id":"2512.04552","title":"RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS","created":"2025-12-04","cited_by_count":4,"area":"alignment"},{"id":"2311.07587","title":"Frontier Language Models are not Robust to Adversarial Arithmetic, or \"What do I need to say so you agree 2+2=5?","created":"2023-11-08","cited_by_count":3,"area":"alignment"},{"id":"2506.04462","title":"Watermarking Degrades Alignment in Language Models: Analysis and Mitigation","created":"2025-06-04","cited_by_count":3,"area":"alignment"},{"id":"2510.08256","title":"Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2405.01280","title":"Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation","created":"2024-05-02","cited_by_count":1,"area":"alignment"},{"id":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","cited_by_count":0,"area":"alignment"},{"id":"2601.11574","title":"GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2605.00236","title":"Attention Is Where You Attack","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.30873","title":"Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences","created":"2026-05-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}