{"total":55,"rows":[{"id":"2602.04863","title":"Subliminal Effects in Your Data: A General Mechanism via Log-Linearity","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2604.25891","title":"Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers","created":"2026-04-28","cited_by_count":17,"area":null},{"id":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2604.17031","title":"Where is the Mind? Persona Vectors and LLM Individuation","created":"2026-04-18","cited_by_count":10,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2602.08563","title":"Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs","created":"2026-02-09","cited_by_count":6,"area":"safety"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2606.04071","title":"Covert Influence Between Language Models","created":"2026-06-02","cited_by_count":6,"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":"2604.13051","title":"The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious","created":"2026-03-17","cited_by_count":5,"area":"alignment"},{"id":"2604.13076","title":"Alignment midtraining for animals","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2603.01204","title":"Subliminal Signals in Preference Labels","created":"2026-03-01","cited_by_count":3,"area":"alignment"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2608.05734","title":"Subliminal Learning is Non-Semantic Distillation","created":"2026-08-06","cited_by_count":3,"area":"mechinterp"},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2608.31079","title":"Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2601.04369","title":"Generalization to Political Beliefs from Fine-Tuning on Sports Team Preferences","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.13752","title":"Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2604.10022","title":"Weird Generalization is Weirdly Brittle","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.06846","title":"Narrow Secret Loyalty Dodges Black-Box Audits","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2606.20512","title":"Probe-and-Refine Tuning of Repository Guidance for Coding Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.03640","title":"Revealing Hidden Model Behaviors with Task-Specific Self-Reports","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.14888","title":"Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.23394","title":"Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2607.26173","title":"Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.28607","title":"Inducing language models to assert their own consciousness restores human beliefs and values","created":"2026-07-30","cited_by_count":1,"area":"alignment"},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2608.15507","title":"Do Language Models Consistently Encode the Current Year?","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2609.01091","title":"Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation","created":"2026-09-01","cited_by_count":1,"area":"distill"},{"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":"2609.25518","title":"Matryoshka attribution: Learning to attribute language model outputs to representations and weights","created":"2026-09-22","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":"2512.18551","title":"Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2603.04407","title":"Semantic Containment as a Fundamental Property of Emergent Misalignment","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.06816","title":"\"Dark Triad\" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.28925","title":"Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.23565","title":"Understanding Goal Generalisation in Sequential Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.07963","title":"Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs","created":"2026-06-06","cited_by_count":0,"area":"safety"},{"id":"2606.16242","title":"Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"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":"2606.29646","title":"Fuzzing Large Language Models to Elicit Hidden Behaviours","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2607.03478","title":"Demonstrating Generalization Failures via Mixtures of Conditional Policies","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.26462","title":"Diff Mining: Logit Differences Reveal Finetuning Objectives","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.06851","title":"You Are What You Read: Misalignment via In-Context Persona Induction","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.10883","title":"Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.33150","title":"Generalization Dynamics of LM Pre-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35805","title":"Alignment Forecasting: Predicting Misalignment From Training Data","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2610.01652","title":"Iterative Policy Refinement through Semantic Rollout Analysis","created":"2026-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2610.09384","title":"The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12129","title":"An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14937","title":"Predicting how model propensities generalize out of distribution","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}