{"total":90,"rows":[{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2512.15674","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","created":"2025-12-17","cited_by_count":52,"area":null},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2505.24535","title":"Beyond Linear Steering: Unified Multi-Attribute Control for Language Models","created":"2025-05-30","cited_by_count":25,"area":null},{"id":"2506.10150","title":"When Large Language Models are Reliable for Judging Empathic Communication","created":"2025-06-11","cited_by_count":21,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2504.16728","title":"IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery","created":"2025-04-23","cited_by_count":19,"area":null},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18,"area":null},{"id":"2510.01645","title":"Position: Privacy Is Not Just Memorization!","created":"2025-10-02","cited_by_count":17,"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":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2512.17639","title":"Linear Personality Probing and Steering in LLMs: A Big Five Study","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"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":"2602.05910","title":"Chunky Post-Training: Data Driven Failures of Generalization","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2603.05414","title":"Emergent Introspection in AI is Content-Agnostic","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2504.01850","title":"Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2510.08506","title":"Neologism Learning for Controllability and Self-Verbalization","created":"2025-10-09","cited_by_count":6,"area":null},{"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":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","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":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2504.04600","title":"Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond","created":"2025-04-06","cited_by_count":3,"area":null},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2507.08249","title":"Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2512.24560","title":"Localized Calibrated Uncertainty in Code Language Models","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.14388","title":"A Low-Rank Subspace Analysis of LLM Interventions","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2608.20442","title":"Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2504.20980","title":"Jekyll-and-Hyde Tipping Point in an AI's Behavior","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2507.11544","title":"The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2603.08723","title":"Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation","created":"2026-02-17","cited_by_count":2,"area":null},{"id":"2605.18738","title":"What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models","created":"2026-05-18","cited_by_count":2,"area":null},{"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":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2608.12036","title":"Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2509.19325","title":"How Much of Your Data Can Suck? Thresholds for Domain Performance and Emergent Misalignment in LLMs","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.09287","title":"From Model Training to Model Raising","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2512.21439","title":"Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.25861","title":"Why Safety Probes Catch Liars But Miss Fanatics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2603.28561","title":"Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems","created":"2026-03-30","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":"2605.02751","title":"Mitigating Misalignment Contagion by Steering with Implicit Traits","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.07462","title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","created":"2026-05-08","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":"2606.09475","title":"Emergent alignment and the projectability of ethical personas","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":"2606.27757","title":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","created":"2026-06-26","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":"2607.23394","title":"Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2608.12894","title":"BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavarian","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"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":"2504.13777","title":"Beyond Misinformation: A Conceptual Framework for Studying AI Hallucinations in (Science) Communication","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2510.20190","title":"The Lock-In Phase Hypothesis: Identity Consolidation as a Precursor to AGI","created":"2025-10-23","cited_by_count":0,"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":"2603.21491","title":"Stable but Wrong: When Learning Stabilizes Away from the Truth","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.05273","title":"Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.25639","title":"Large language models eroding science understanding: an empirical study of malignment","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.00994","title":"Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.16215","title":"Fully Open Meditron: An Auditable Pipeline for Clinical LLMs","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.24583","title":"Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol","created":"2026-05-23","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":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","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":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"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":"2607.26389","title":"Misalignment Has a Personality: A Big Five Account of Emergent Misalignment","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.29118","title":"Emergent Misalignment Is Not Magical","created":"2026-08-29","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":"2609.22934","title":"Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"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":"2610.11012","title":"Distillation for Incrimination and Distillation for Capabilities","created":"2026-10-07","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}