{"total":19,"rows":[{"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":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2605.26242","title":"Can LLMs Introspect? A Reality Check","created":"2026-05-25","cited_by_count":12,"area":null},{"id":"2603.05414","title":"Emergent Introspection in AI is Content-Agnostic","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2606.04071","title":"Covert Influence Between Language Models","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2604.03058","title":"Verbalizing LLMs' assumptions to explain and control sycophancy","created":"2026-04-03","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":"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":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.12373","title":"Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2604.22027","title":"Shared Lexical Task Representations Explain Behavioral Variability In LLMs","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2604.15010","title":"What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2606.02609","title":"Building Better Activation Oracles","created":"2026-05-23","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":"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":"2609.32449","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":"2610.17495","title":"A Sense of Proprioception in Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}