{"total":48,"rows":[{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"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Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2405.08460","title":"Is Your LLM Outdated?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":"2506.00723","title":"Pitfalls in Evaluating Language Model Forecasters","created":"2025-05-31","cited_by_count":23,"area":null},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21,"area":null},{"id":"2406.04446","title":"Can Language Models Use Forecasting Strategies?","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2408.06578","title":"OpenEP: Open-Ended Future Event Prediction","created":"2024-08-13","cited_by_count":11,"area":null},{"id":"2412.09049","title":"Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues","created":"2024-12-12","cited_by_count":11,"area":null},{"id":"2505.11613","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2604.07355","title":"Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets","created":"2026-03-28","cited_by_count":10,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"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":"2505.12349","title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2506.16702","title":"Large Language Models as Psychological Simulators: A Methodological Guide","created":"2025-06-20","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":"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":"2606.10398","title":"Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting","created":"2026-06-09","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":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.11654","title":"The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience","created":"2026-06-10","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":"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":"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":"2502.10554","title":"Benchmarking the rationality of AI decision making using the transitivity axiom","created":"2025-02-14","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":"2505.24622","title":"Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data","created":"2025-05-30","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":"2606.11613","title":"Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting","created":"2026-06-10","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":"2609.01337","title":"LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2512.23889","title":"How Large Language Models Systematically Misrepresent American Climate Opinions","created":"2025-12-29","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":"2603.04325","title":"Scalable Evaluation of the Realism of Synthetic Environmental Augmentations in Images","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.08606","title":"Extrapolating Volition with Recursive Information Markets","created":"2026-04-08","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":"2605.27394","title":"Human-AI Collaboration for Estimating Scientific Replicability","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.28070","title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","created":"2026-06-26","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":"2607.09921","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":"2608.04008","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":"2608.20421","title":"Six misconceptions about large language models: A minimal model and diagnostic taxonomy","created":"2026-08-19","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":"2609.26303","title":"Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target","created":"2026-09-22","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":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}