{"total":78,"rows":[{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"area":null},{"id":"2402.19379","title":"Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy","created":"2024-02-29","cited_by_count":67,"area":null},{"id":"2405.02079","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","created":"2024-05-03","cited_by_count":36,"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Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2405.08460","title":"Is Your LLM Outdated?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":"2403.03407","title":"Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations","created":"2024-03-06","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":"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":"2410.14651","title":"Real-time Factuality Assessment from Adversarial Feedback","created":"2024-10-18","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":"2408.06578","title":"OpenEP: Open-Ended Future Event Prediction","created":"2024-08-13","cited_by_count":11,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"area":null},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2507.04562","title":"Evaluating LLMs on Real-World Forecasting Against Expert Forecasters","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"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":"2601.13717","title":"Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff","created":"2026-01-20","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":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2605.00420","title":"Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2601.22444","title":"Automating Forecasting Question Generation and Resolution for AI Evaluation","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2605.00844","title":"The Oracle's Fingerprint: Correlated AI Forecasting Errors and the Limits of Bias Transmission","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2609.02797","title":"Dutch Books for Language Models","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2408.17070","title":"Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2507.23163","title":"Argumentatively Coherent Judgmental Forecasting","created":"2025-07-30","cited_by_count":2,"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":"2511.18394","title":"Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2605.03762","title":"OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.16358","title":"LEAF: A Living Benchmark for Event-Augmented Forecasting","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.21491","title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2606.18686","title":"ForecastBench-Sim: A Simulated-World Forecasting Benchmark","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2606.29661","title":"Diversity is the Strength of the AI Crowd","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","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":"2609.00747","title":"Can Large Language Models Forecast What Researchers Study Next?","created":"2026-09-01","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":"2502.13410","title":"Tell Me Why: Incentivizing Explanations","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2511.14214","title":"Do Large Language Models (LLMs) Understand Chronology?","created":"2025-11-18","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":"2607.14051","title":"Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters","created":"2026-07-15","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":"2608.20920","title":"ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.30110","title":"Can LLMs Take the Pulse of the Economy? A Real-Time Evaluation of LLM Nowcasts on Macroeconomic Indicators","created":"2026-08-31","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":"2412.15239","title":"Modeling Story Expectations: A Generative Framework using LLMs","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2506.13036","title":"Forecast-Then-Optimize Deep Learning Methods","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2510.09146","title":"Score-Based Density Estimation from Pairwise Comparisons","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.16551","title":"From Reviews to Actionable Insights: An LLM-Based Approach for Attribute and Feature Extraction","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2602.00758","title":"Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study","created":"2026-01-31","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":"2602.21229","title":"Forecasting Future Language: Context Design for Mention Markets","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.22672","title":"Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most","created":"2026-05-21","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":"2605.31069","title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","created":"2026-05-29","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":"2607.06656","title":"Robust Human-AI Complementarity under Uncertainty","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.09921","title":"Global Merger-Arbitrage Forecasting with Language Models","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.26981","title":"OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.03569","title":"Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities","created":"2026-08-04","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":"2608.23248","title":"Future Querying: Can LLMs Serve as Implicit Medical World Models?","created":"2026-08-24","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":"2609.12101","title":"When Do Language Models Add Value? Relative Competence in Hybrid Event Forecasting","created":"2026-09-10","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":"2609.32885","title":"Can LLMs Predict the Future? A Brier Score Analysis of Prediction Markets","created":"2026-09-26","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":"2609.35805","title":"Alignment Forecasting: Predicting Misalignment From Training Data","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.35879","title":"CruxBench: A Benchmark of Information Discovery","created":"2026-09-26","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},{"id":"2610.02202","title":"ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}