{"total":13,"rows":[{"id":"2502.16797","title":"Forecasting Rare Language Model Behaviors","created":"2025-02-24","cited_by_count":19,"area":null},{"id":"2412.12480","title":"Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?","created":"2024-12-17","cited_by_count":15,"area":null},{"id":"2602.06791","title":"Rare Event Analysis of Large Language Models","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2506.02058","title":"Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2606.29623","title":"SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.18454","title":"Estimating Rare Events in Language Models with Proper Evaluation","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2605.15134","title":"Training ML Models with Predictable Failures","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.31105","title":"BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.32061","title":"Contract monitoring: governing AI via separation of powers","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33638","title":"Quantifying Behavioral Tails in Black-Box Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.04976","title":"Priced Guidance: Can Language Models Generate Future Research Ideas?","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}