{"total":11,"rows":[{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2504.11524","title":"HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation","created":"2025-04-15","cited_by_count":37,"area":null},{"id":"2602.11246","title":"How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2510.14073","title":"Exploratory Causal Inference in SAEnce","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2602.19458","title":"ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2508.19780","title":"Interestingness First Classifiers","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2606.02632","title":"Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2610.01627","title":"What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}