{"total":19,"rows":[{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2509.05291","title":"Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining","created":"2025-09-05","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":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2506.05579","title":"When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2508.00545","title":"Foundations of Interpretable Models","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2605.04970","title":"Skill Neologisms: Towards Skill-based Continual Learning","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","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":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2507.03866","title":"A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime","created":"2025-07-05","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":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2607.26825","title":"From Found to Designed: Concepts as a Design Axis for Large Language Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.16894","title":"An Investigation of the NeurIPS and ICML 2025 Position Tracks","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.00443","title":"(V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}