{"total":69,"rows":[{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","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":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2505.23556","title":"Understanding Refusal in Language Models with Sparse Autoencoders","created":"2025-05-29","cited_by_count":29,"area":"alignment"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2506.00253","title":"Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race","created":"2025-05-30","cited_by_count":15,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2512.13655","title":"Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation","created":"2025-12-15","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":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8,"area":"alignment"},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7,"area":"alignment"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"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":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5,"area":"alignment"},{"id":"2406.08124","title":"Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2509.12934","title":"The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features","created":"2025-09-16","cited_by_count":5,"area":"alignment"},{"id":"2506.16078","title":"Probing the Robustness of Large Language Models Safety to Latent Perturbations","created":"2025-06-19","cited_by_count":4,"area":"alignment"},{"id":"2602.07639","title":"Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization","created":"2026-02-07","cited_by_count":4,"area":"alignment"},{"id":"2505.01162","title":"On the Limitations of Steering in Language Model Alignment","created":"2025-05-02","cited_by_count":3,"area":"alignment"},{"id":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2602.07356","title":"Controllable Value Alignment in Large Language Models through Neuron-Level Editing","created":"2026-02-07","cited_by_count":3,"area":"alignment"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2501.05336","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","created":"2025-01-09","cited_by_count":2,"area":"alignment"},{"id":"2603.03326","title":"Controllable and explainable personality sliders for LLMs at inference time","created":"2026-02-10","cited_by_count":2,"area":"alignment"},{"id":"2603.05773","title":"Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models","created":"2026-03-06","cited_by_count":2,"area":"alignment"},{"id":"2606.03131","title":"HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2603.04355","title":"Efficient Refusal Ablation in LLM through Optimal Transport","created":"2026-03-04","cited_by_count":1,"area":"alignment"},{"id":"2603.13359","title":"From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions","created":"2026-03-09","cited_by_count":1,"area":"alignment"},{"id":"2605.16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2605.16600","title":"Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space","created":"2026-05-15","cited_by_count":1,"area":"alignment"},{"id":"2605.17413","title":"Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications","created":"2026-05-17","cited_by_count":1,"area":"alignment"},{"id":"2605.21706","title":"Latent-space Attacks for Refusal Evasion in Language Models","created":"2026-05-20","cited_by_count":1,"area":"alignment"},{"id":"2605.28802","title":"Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2606.22686","title":"The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs","created":"2026-06-21","cited_by_count":1,"area":"alignment"},{"id":"2607.01802","title":"On the Limits of Steering Vectors for Preference-Aligned Generation","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2607.19243","title":"Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs","created":"2026-07-21","cited_by_count":1,"area":"alignment"},{"id":"2609.03887","title":"Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness","created":"2026-09-03","cited_by_count":1,"area":"alignment"},{"id":"2506.24056","title":"Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness","created":"2025-06-30","cited_by_count":0,"area":"alignment"},{"id":"2602.04000","title":"After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona Interactions","created":"2026-02-03","cited_by_count":0,"area":"alignment"},{"id":"2603.03000","title":"Why Does RLAIF Work At All?","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2603.05839","title":"Evaluating LLM Alignment With Human Trust Models","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2603.06264","title":"Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2603.15647","title":"Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing","created":"2026-03-04","cited_by_count":0,"area":"alignment"},{"id":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","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":"2606.04160","title":"Decomposing Refusal Steering in Mixture-of-Experts Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.20508","title":"What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?","created":"2026-06-18","cited_by_count":0,"area":"alignment"},{"id":"2606.21645","title":"Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models","created":"2026-06-19","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2608.03892","title":"Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.07509","title":"PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2608.30197","title":"ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.06289","title":"Steering Geometry: Validating Human Value Geometry in LLM Steering Space","created":"2026-09-05","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"},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.34771","title":"When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.38389","title":"The Geometry of Harmfulness in Multi-Turn Attacks","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.38645","title":"Alignment via Training Against Probes Without Losing Monitorability","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.19365","title":"DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}