{"total":82,"rows":[{"id":"2602.20031","title":"Latent Introspection: Models Can Detect Prior Concept Injections","created":"2026-02-23","cited_by_count":14,"area":null},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2605.26242","title":"Can LLMs Introspect? A Reality Check","created":"2026-05-25","cited_by_count":12,"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":"2606.23525","title":"Self-Compacting Language Model Agents","created":"2026-06-22","cited_by_count":11,"area":"agents"},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2601.10242","title":"Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?","created":"2026-01-15","cited_by_count":8,"area":null},{"id":"2606.29490","title":"Reported Confidence in LLMs Tracks Commitment More Than Correctness","created":"2026-06-28","cited_by_count":8,"area":null},{"id":"2603.05414","title":"Emergent Introspection in AI is Content-Agnostic","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"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":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"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":"2606.04071","title":"Covert Influence Between Language Models","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2602.06941","title":"Endogenous Resistance to Activation Steering in Language Models","created":"2026-02-06","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"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":"2604.17465","title":"Language models recognize dropout and Gaussian noise applied to their activations","created":"2026-04-19","cited_by_count":5,"area":null},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2602.11824","title":"Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models","created":"2026-02-12","cited_by_count":4,"area":"mllm"},{"id":"2606.12747","title":"Prefill Awareness in Large Language Models","created":"2026-06-10","cited_by_count":4,"area":"safety"},{"id":"2606.20097","title":"HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization","created":"2026-06-18","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":"2601.08017","title":"Representations of Text and Images Align From Layer One","created":"2026-01-12","cited_by_count":3,"area":"mllm"},{"id":"2601.13383","title":"A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge","created":"2026-01-19","cited_by_count":3,"area":"agents"},{"id":"2601.15334","title":"No Reliable Evidence of Self-Reported Sentience in Small Large Language Models","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2602.02467","title":"Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2603.20276","title":"Me, Myself, and $\\pi$ : Evaluating and Explaining LLM Introspection","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.08551","title":"Self-Sovereign Agent","created":"2026-03-04","cited_by_count":2,"area":"agents"},{"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":"2605.31514","title":"If LLMs Have Human-Like Attributes, Then So Does Age of Empires II","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2607.04277","title":"Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement","created":"2026-07-05","cited_by_count":2,"area":"synth"},{"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":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2604.12128","title":"Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.21043","title":"Strategic Polysemy in AI Discourse: A Philosophical Analysis of Language, Hype, and Power","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.06965","title":"AI and Consciousness: Shifting Focus Towards Tractable Questions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.20075","title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.23700","title":"Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.14111","title":"Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.30980","title":"Evaluating and Improving LLM Self-Modeling","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2602.10352","title":"Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.14910","title":"Position: Introspective Experience from Conversational Environments as a Path to Better Learning","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.00228","title":"Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries","created":"2026-03-31","cited_by_count":0,"area":"safety"},{"id":"2604.05469","title":"Task Ecologies and the Evolution of World-Tracking Representations in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.11337","title":"Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.25067","title":"Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2604.27169","title":"Semantic Structure of Feature Space in Large Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"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":"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":"2605.27681","title":"Behavioural Analysis of Alignment Faking","created":"2026-05-26","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":"2606.15507","title":"Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2606.22085","title":"Can Reasoning Models Detect Changes to their Chains of Thought?","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2607.04222","title":"Unsupervised Features Mining via Activation Geometry","created":"2026-07-05","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":"2608.13258","title":"Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.15304","title":"Understanding Cognition-Induced Risks in Agentic AI Systems","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"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":"2608.31084","title":"Verbalizing Multi-Token Concepts in LLMs","created":"2026-08-31","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":"2609.22362","title":"Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.25021","title":"\"As a Language Model...\": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.29494","title":"Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.32449","title":"Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32670","title":"What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35108","title":"A mechanistic study of language model introspection","created":"2026-09-28","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":"2609.35591","title":"Language Models Act on Hidden Valence","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35618","title":"From cacophony to hierarchy: a principled framework for assessing AI consciousness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"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":"2610.20179","title":"Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}