{"total":52,"rows":[{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"area":null},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2510.17638","title":"LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena","created":"2025-10-20","cited_by_count":40,"area":null},{"id":"2305.10613","title":"Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning","created":"2023-05-17","cited_by_count":37,"area":null},{"id":"2412.18544","title":"Consistency Checks for Language Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2405.08460","title":"Is Your LLM Outdated? A Deep Look at Temporal Generalization","created":"2024-05-14","cited_by_count":26,"area":null},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24,"area":null},{"id":"2506.00723","title":"Pitfalls in Evaluating Language Model Forecasters","created":"2025-05-31","cited_by_count":23,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2310.01880","title":"AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2506.00794","title":"Predicting Empirical AI Research Outcomes with Language Models","created":"2025-06-01","cited_by_count":17,"area":null},{"id":"2406.04446","title":"Can Language Models Use Forecasting Strategies?","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2604.14199","title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","created":"2026-04-03","cited_by_count":12,"area":null},{"id":"2302.00805","title":"Conditioning Predictive Models: Risks and Strategies","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2312.06941","title":"Humans vs Large Language Models: Judgmental Forecasting in an Era of Advanced AI","created":"2023-12-12","cited_by_count":11,"area":null},{"id":"2408.06578","title":"OpenEP: Open-Ended Future Event Prediction","created":"2024-08-13","cited_by_count":11,"area":null},{"id":"2402.13093","title":"Event-level Knowledge Editing","created":"2024-02-20","cited_by_count":9,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"area":null},{"id":"2502.19676","title":"FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2503.05628","title":"Superintelligence Strategy: Expert Version","created":"2025-03-07","cited_by_count":7,"area":null},{"id":"2305.14847","title":"Drafting Event Schemas using Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2507.19477","title":"Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2512.16030","title":"Do Large Language Models Know What They Don't Know? Kalshibench: A New Benchmark for Evaluating Epistemic Calibration via Prediction Markets","created":"2025-12-17","cited_by_count":5,"area":null},{"id":"2509.20645","title":"Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.23936","title":"Do Language Models Update their Forecasts with New Information?","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2511.21570","title":"From Prediction to Foresight: The Role of AI in Designing Responsible Futures","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.17234","title":"All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2607.18269","title":"Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2608.02985","title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2411.14042","title":"Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2512.22625","title":"The Wisdom of Deliberating AI Crowds: Does Deliberation Improve LLM-Based Forecasting?","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2604.15719","title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.26106","title":"Evaluating Strategic Reasoning in Forecasting Agents","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2607.24573","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.04009","title":"SocietyBench: Forecasting Counterfactual Social-World Evolution","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.01337","title":"LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2410.09038","title":"SimpleStrat: Diversifying Language Model Generation with Stratification","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2502.15332","title":"Detecting Future-related Contexts of Entity Mentions","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2602.08889","title":"Scalable Delphi: Large Language Models for Structured Risk Estimation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.26074","title":"StakeBench: Evaluating Language Understanding Grounded in Market Commitment","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.04008","title":"WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.16795","title":"Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.28482","title":"How Proper Scoring Rules Shape LLM Forecasting","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.22246","title":"The Corroboration Illusion: When More News Makes LLM Forecasts Less True","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.23916","title":"Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.33257","title":"Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}