{"total":42,"rows":[{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2410.09760","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","created":"2024-10-13","cited_by_count":37,"area":"alignment"},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2309.09055","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","created":"2023-09-16","cited_by_count":20,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"area":"alignment"},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2406.04879","title":"A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques","created":"2024-06-07","cited_by_count":16,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"area":"alignment"},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2407.02987","title":"LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models","created":"2024-07-03","cited_by_count":7,"area":"alignment"},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2409.14836","title":"Orthogonal Finetuning for Direct Preference Optimization","created":"2024-09-23","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2412.12865","title":"Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models","created":"2024-12-17","cited_by_count":5,"area":"alignment"},{"id":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","cited_by_count":5,"area":"alignment"},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2310.00819","title":"Parameter-Efficient Tuning Helps Language Model Alignment","created":"2023-10-01","cited_by_count":4,"area":"alignment"},{"id":"2405.20215","title":"TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models","created":"2024-05-30","cited_by_count":4,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2508.17637","title":"Weights-Rotated Preference Optimization for Large Language Models","created":"2025-08-25","cited_by_count":3,"area":"alignment"},{"id":"2601.06352","title":"CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation","created":"2026-01-09","cited_by_count":3,"area":"alignment"},{"id":"2603.22563","title":"Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling","created":"2026-03-23","cited_by_count":3,"area":"alignment"},{"id":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2503.13690","title":"Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization","created":"2025-03-17","cited_by_count":2,"area":"alignment"},{"id":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2502.16691","title":"Responsible Federated LLMs via Safety Filtering and Constitutional AI","created":"2025-02-23","cited_by_count":1,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2601.09718","title":"StatLLaMA: Multi-Stage training for domain-optimized statistical large language models","created":"2025-12-26","cited_by_count":0,"area":"alignment"},{"id":"2605.09777","title":"EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent","created":"2026-05-10","cited_by_count":0,"area":"alignment"},{"id":"2605.21558","title":"From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.28669","title":"LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment","created":"2026-07-25","cited_by_count":0,"area":"alignment"},{"id":"2608.13069","title":"Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds","created":"2026-08-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}