{"total":77,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2406.05644","title":"How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States","created":"2024-06-09","cited_by_count":98,"area":"alignment"},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83,"area":"alignment"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60,"area":"alignment"},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50,"area":"alignment"},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"area":"alignment"},{"id":"2501.12895","title":"Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback","created":"2025-01-22","cited_by_count":41,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2406.04412","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment","created":"2024-06-06","cited_by_count":27,"area":"alignment"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2401.06785","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","created":"2024-01-06","cited_by_count":25,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2410.15633","title":"GATEAU: Selecting Influential Samples for Long Context Alignment","created":"2024-10-21","cited_by_count":20,"area":"alignment"},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2410.03717","title":"Revisiting the Superficial Alignment Hypothesis","created":"2024-09-27","cited_by_count":12,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2406.18118","title":"SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance","created":"2024-06-26","cited_by_count":9,"area":"alignment"},{"id":"2506.04463","title":"Aligning Large Language Models with Implicit Preferences from User-Generated Content","created":"2025-06-04","cited_by_count":9,"area":"alignment"},{"id":"2403.14238","title":"Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection","created":"2024-03-21","cited_by_count":8,"area":"alignment"},{"id":"2410.06491","title":"Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack","created":"2024-10-09","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":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2503.19041","title":"LookAhead Tuning: Safer Language Models via Partial Answer Previews","created":"2025-03-24","cited_by_count":7,"area":"alignment"},{"id":"2505.00038","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","created":"2025-04-29","cited_by_count":7,"area":"alignment"},{"id":"2506.07434","title":"Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding","created":"2025-06-09","cited_by_count":7,"area":"alignment"},{"id":"2406.11474","title":"How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment","created":"2024-06-17","cited_by_count":6,"area":"alignment"},{"id":"2411.10912","title":"SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment","created":"2024-11-16","cited_by_count":6,"area":"alignment"},{"id":"2502.13946","title":"Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region","created":"2025-02-19","cited_by_count":6,"area":"alignment"},{"id":"2410.14184","title":"MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time","created":"2024-10-18","cited_by_count":5,"area":"alignment"},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2408.00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","created":"2024-08-01","cited_by_count":4,"area":"alignment"},{"id":"2508.09473","title":"NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs","created":"2025-08-13","cited_by_count":4,"area":"alignment"},{"id":"2501.14294","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","created":"2025-01-24","cited_by_count":3,"area":"alignment"},{"id":"2507.16679","title":"PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2603.06797","title":"Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment","created":"2026-03-06","cited_by_count":3,"area":"alignment"},{"id":"2406.12416","title":"Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models","created":"2024-06-18","cited_by_count":2,"area":"alignment"},{"id":"2410.00508","title":"FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization","created":"2024-10-01","cited_by_count":2,"area":"alignment"},{"id":"2502.11681","title":"RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars","created":"2025-02-17","cited_by_count":2,"area":"alignment"},{"id":"2502.20795","title":"Test-Time Alignment for Large Language Models via Textual Model Predictive Control","created":"2025-02-28","cited_by_count":2,"area":"alignment"},{"id":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2,"area":"alignment"},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2604.17132","title":"Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding","created":"2026-04-18","cited_by_count":2,"area":"alignment"},{"id":"2605.18309","title":"Alignment Dynamics in LLM Fine-Tuning","created":"2026-05-18","cited_by_count":2,"area":"alignment"},{"id":"2606.11201","title":"To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending","created":"2026-04-22","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":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2505.19700","title":"Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2508.04626","title":"P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis","created":"2025-08-06","cited_by_count":1,"area":"alignment"},{"id":"2511.00509","title":"Reimagining Safety Alignment with An Image","created":"2025-11-01","cited_by_count":1,"area":"alignment"},{"id":"2605.24154","title":"Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs","created":"2026-05-22","cited_by_count":1,"area":"alignment"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2510.20129","title":"SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models","created":"2025-10-23","cited_by_count":0,"area":"alignment"},{"id":"2602.08377","title":"Reinforcement Learning with Backtracking Feedback","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.25342","title":"MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2605.30526","title":"Measuring, Localizing, and Ablating Alignment Signatures in LLMs","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2606.04168","title":"When Autoregressive Consistency Hurts Safety Alignment","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2607.03453","title":"Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning","created":"2026-07-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}