{"total":59,"rows":[{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"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":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2503.07513","title":"Language Models Fail to Introspect About Their Knowledge of Language","created":"2025-03-10","cited_by_count":30,"area":null},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2504.14045","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","created":"2025-04-18","cited_by_count":23,"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":"2508.14802","title":"Privileged Self-Access Matters for Introspection in AI","created":"2025-08-20","cited_by_count":22,"area":null},{"id":"2510.24797","title":"Large Language Models Report Subjective Experience Under Self-Referential Processing","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2509.21545","title":"Evidence for Limited Metacognition in LLMs","created":"2025-09-25","cited_by_count":12,"area":null},{"id":"2510.05092","title":"Learning to Interpret Weight Differences in Language Models","created":"2025-10-06","cited_by_count":11,"area":null},{"id":"2604.16812","title":"Introspection Adapters: Training LLMs to Report Their Learned Behaviors","created":"2026-04-18","cited_by_count":11,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2505.11614","title":"Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2509.00591","title":"Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","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":"2507.06253","title":"Emergent misalignment as prompt sensitivity: A research note","created":"2025-07-06","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":"2605.25459","title":"From Simulation to Enaction: Post-trained language models recognize and react to their own generations","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.32038","title":"Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.18777","title":"Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2511.04875","title":"Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.02605","title":"Fine-Tuning Language Models to Know What They Know","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.25922","title":"Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2508.18467","title":"The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game","created":"2025-08-25","cited_by_count":1,"area":null},{"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":"2604.28082","title":"Characterizing the Consistency of the Emergent Misalignment Persona","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2607.02755","title":"Out-of-Distribution Generalization of Risk Aversion in Language Models","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","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":"2508.00741","title":"Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data","created":"2025-08-01","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":"2602.08449","title":"When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment","created":"2026-02-09","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":"2605.05080","title":"The Shared Latent Structure of LLM Psychometric Responses","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.20382","title":"Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.00545","title":"The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.06380","title":"Emergent Language as an Approach to Conscious AI","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.14250","title":"The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.18553","title":"Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.28137","title":"Asymmetric Communication: Large Language Models and Language Games","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.04347","title":"Introspecting Alignment Shifts Beyond Behaviors Implanted Through Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20569","title":"Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.00608","title":"Investigating Assistant Bias in LLM User Simulators Using a Role Vector","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.00904","title":"In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.09899","title":"Strangers to Themselves: What Language Models Say About Themselves Is Generic","created":"2026-09-09","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":"2609.35261","title":"Imprint Reader: From Weight-Update Readout to Behavioral Intervention","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35409","title":"AwarenessBench: Assessing Cognitive Capabilities of Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06174","title":"Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17495","title":"A Sense of Proprioception in Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}