{"total":32,"rows":[{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30,"area":null},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2409.20553","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","created":"2024-09-30","cited_by_count":25,"area":null},{"id":"2401.03910","title":"A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates","created":"2024-01-08","cited_by_count":23,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2504.13938","title":"Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection","created":"2025-04-15","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2507.21488","title":"Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2312.02091","title":"Physics simulation capabilities of LLMs","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2410.20811","title":"Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"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":"2408.13438","title":"Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2603.01822","title":"Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2509.22755","title":"Concept activation vectors: a unifying view and adversarial attacks","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.13316","title":"Visual Interestingness Decoded: How GPT-4o Mirrors Human Interests","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2511.01932","title":"Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2412.11205","title":"Concept Learning in the Wild: Towards Algorithmic Understanding of Neural Networks","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2504.00831","title":"Example-Based Concept Analysis Framework for Deep Weather Forecast Models","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2605.15688","title":"$\\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.20628","title":"Human Decision-Making with AI Assistance under Correlated Features","created":"2026-05-27","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":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}