{"total":38,"rows":[{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31,"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":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"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":"2507.11316","title":"Internal Value Alignment in Large Language Models through Controlled Value Vector Activation","created":"2025-07-15","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":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2507.03662","title":"Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs","created":"2025-07-04","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":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"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":"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":"2508.20766","title":"Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection","created":"2025-08-28","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":"2602.00986","title":"Sparse Reward Subsystem in Large Language Models","created":"2026-02-01","cited_by_count":4,"area":"alignment"},{"id":"2604.18901","title":"Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams","created":"2026-04-20","cited_by_count":4,"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":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2,"area":"alignment"},{"id":"2603.27518","title":"Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs","created":"2026-03-29","cited_by_count":2,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2511.21737","title":"Polarity-Aware Probing for Quantifying Latent Alignment in Language Models","created":"2025-11-21","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":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","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":"2607.02714","title":"Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale","created":"2026-07-02","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":"2603.05839","title":"Evaluating LLM Alignment With Human Trust Models","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2605.28722","title":"Multi-Adapter Representation Interventions via Energy Calibration","created":"2026-05-27","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":"2608.30197","title":"ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2608.30902","title":"Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.32717","title":"LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations","created":"2026-09-26","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":"2610.19365","title":"DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}