{"total":71,"rows":[{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","cited_by_count":23,"area":null},{"id":"2510.11288","title":"Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs","created":"2025-10-13","cited_by_count":17,"area":null},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","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":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2604.17031","title":"Where is the Mind? Persona Vectors and LLM Individuation","created":"2026-04-18","cited_by_count":10,"area":null},{"id":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2511.02022","title":"Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior","created":"2025-11-03","cited_by_count":8,"area":null},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2507.06253","title":"Emergent misalignment as prompt sensitivity: A research note","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2602.14777","title":"Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment","created":"2026-02-16","cited_by_count":6,"area":"alignment"},{"id":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6,"area":"mllm"},{"id":"2508.20015","title":"Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5,"area":"safety"},{"id":"2510.08203","title":"Memory Retrieval and Consolidation in Large Language Models through Function Tokens","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2603.04426","title":"Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2603.29805","title":"From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2604.08169","title":"Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2602.00298","title":"Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning","created":"2026-01-30","cited_by_count":3,"area":"safety"},{"id":"2606.06223","title":"From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents","created":"2026-06-04","cited_by_count":3,"area":"agents"},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.08682","title":"Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation","created":"2026-06-07","cited_by_count":2,"area":"mechinterp"},{"id":"2607.09053","title":"An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2511.17869","title":"The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems","created":"2025-11-22","cited_by_count":1,"area":"alignment"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.19101","title":"Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models","created":"2026-02-22","cited_by_count":1,"area":"alignment"},{"id":"2603.12397","title":"Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors","created":"2026-03-12","cited_by_count":1,"area":"lr"},{"id":"2603.25861","title":"Why Safety Probes Catch Liars But Miss Fanatics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.10022","title":"Weird Generalization is Weirdly Brittle","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2604.16697","title":"Surgical Repair of Insecure Code Generation in LLMs","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.28082","title":"Characterizing the Consistency of the Emergent Misalignment Persona","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.12850","title":"Persona-Model Collapse in Emergent Misalignment","created":"2026-05-13","cited_by_count":1,"area":"synth"},{"id":"2605.27676","title":"Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.20225","title":"Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.23700","title":"Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2607.03640","title":"Revealing Hidden Model Behaviors with Task-Specific Self-Reports","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2609.16754","title":"TAME: Token Attribution and Masking for Emergent misalignment","created":"2026-09-15","cited_by_count":1,"area":"alignment"},{"id":"2609.23935","title":"Measuring the Assistant's Harmlessness Preferences on the User Turn","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2609.37914","title":"The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2602.02304","title":"Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.04407","title":"Semantic Containment as a Fundamental Property of Emergent Misalignment","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.10633","title":"Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.16325","title":"Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.20814","title":"What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2607.04510","title":"Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.08212","title":"Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment","created":"2026-08-08","cited_by_count":0,"area":"safety"},{"id":"2608.23476","title":"On the Threat Model of Weird Generalization and Emergent Misalignment","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.23497","title":"Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.29118","title":"Emergent Misalignment Is Not Magical","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.24504","title":"On Emergent Capabilities and Model Merging","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.34970","title":"See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35291","title":"Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37624","title":"Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38379","title":"Aligned Data Can Induce Misalignment via Context Confusion","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00348","title":"Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.18517","title":"Imprinting: Knowledge Distillation Can Shift Student Behavior","created":"2026-10-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}