Automating Forecasting Question Generation and Resolution for AI Evaluation

• URL: http://arxiv.org/abs/2601.22444v1
• Date: Fri, 30 Jan 2026 01:27:23 GMT
• Title: Automating Forecasting Question Generation and Resolution for AI Evaluation
• Abstract summary: We present a system for generating and resolving high-quality forecasting questions automatically and at scale.<n>We use this system to generate 1499 diverse, real-world forecasting questions, and to resolve them several months later.<n>We estimate that our system produces verifiable, unambiguous questions approximately 96% of the time, exceeding the rate of Metaculus.
• Score: 7.5031292927519395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Forecasting future events is highly valuable in decision-making and is a robust measure of general intelligence. As forecasting is probabilistic, developing and evaluating AI forecasters requires generating large numbers of diverse and difficult questions, and accurately resolving them. Previous efforts to automate this laborious work relied on recurring data sources (e.g., weather, stocks), limiting diversity and utility. In this work, we present a system for generating and resolving high-quality forecasting questions automatically and at scale using LLM-powered web research agents. We use this system to generate 1499 diverse, real-world forecasting questions, and to resolve them several months later. We estimate that our system produces verifiable, unambiguous questions approximately 96% of the time, exceeding the rate of Metaculus, a leading human-curated forecasting platform. We also find that our system resolves questions at approximately 95% accuracy. We verify that forecasting agents powered by more intelligent LLMs perform better on these questions (Brier score of 0.134 for Gemini 3 Pro, 0.149 for GPT-5, and 0.179 for Gemini 2.5 Flash). Finally, we demonstrate how our system can be leveraged to directly improve forecasting, by evaluating a question decomposition strategy on a generated question set, yielding a significant improvement in Brier scores (0.132 vs. 0.141).

Related papers

• Scaling Open-Ended Reasoning to Predict the Future [56.672065928345525]
  We train language models to make predictions on open-ended forecasting questions.<n>To scale up training data, we synthesize novel forecasting questions from global events reported in daily news.<n>We find calibration improvements from forecasting training generalize across popular benchmarks.
  arXiv  Detail & Related papers  (2025-12-31T18:59:51Z)
• Bench to the Future: A Pastcasting Benchmark for Forecasting Agents [0.14980193397844666]
  Bench To the Future is a "pastcasting" benchmark with hundreds of high-quality questions for which the resolution is already known.<n>Results suggest that our pastcasting environment can produce results comparable to those based on forecasts using the internet on at-the-time unresolved questions.<n>We intend this to be a living benchmark, with new questions added continually to account for increasing training data cutoff dates.
  arXiv  Detail & Related papers  (2025-06-11T16:18:40Z)
• Consistency Checks for Language Model Forecasters [54.62507816753479]
  We measure the performance of forecasters in terms of the consistency of their predictions on different logically-related questions.<n>We build an automated evaluation system that generates a set of base questions, instantiates consistency checks from these questions, elicits predictions of the forecaster, and measures the consistency of the predictions.
  arXiv  Detail & Related papers  (2024-12-24T16:51:35Z)
• Hybrid Forecasting of Geopolitical Events [71.73737011120103]
  SAGE is a hybrid forecasting system that combines human and machine generated forecasts.<n>The system aggregates human and machine forecasts weighting both for propinquity and based on assessed skill.<n>We show that skilled forecasters who had access to machine-generated forecasts outperformed those who only viewed historical data.
  arXiv  Detail & Related papers  (2024-12-14T22:09:45Z)
• ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities [5.029476863820779]
  ForecastBench is a benchmark for evaluating the accuracy of machine learning systems.<n>ForecastBench is comprised solely of questions about future events that have no known answer at the time of submission.<n>We display system and human scores in a public leaderboard at www.forecastbench.org.
  arXiv  Detail & Related papers  (2024-09-30T00:41:51Z)
• A Practical Probabilistic Benchmark for AI Weather Models [0.7978324349017066]
  We show that two leading AI weather models, i.e. GraphCast and Pangu, are tied on the probabilistic CRPS metric. We also reveal how multiple time-step loss functions, which many data-driven weather models have employed, are counter-productive.
  arXiv  Detail & Related papers  (2024-01-27T05:53:16Z)
• Uncertainty-aware Language Modeling for Selective Question Answering [107.47864420630923]
  We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs. Our approach is model- and data-agnostic, is computationally-efficient, and does not rely on external models or systems.
  arXiv  Detail & Related papers  (2023-11-26T22:47:54Z)
• Forecasting Future World Events with Neural Networks [68.43460909545063]
  Autocast is a dataset containing thousands of forecasting questions and an accompanying news corpus. The news corpus is organized by date, allowing us to precisely simulate the conditions under which humans made past forecasts. We test language models on our forecasting task and find that performance is far below a human expert baseline.
  arXiv  Detail & Related papers  (2022-06-30T17:59:14Z)
• Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees [63.62448343531963]
  We propose a combination of the existing paradigms, sampling responses to be scored by humans intelligently. We observe significant gains in accuracy (19.80% increase on average) and quadratic weighted kappa (QWK) (25.60% on average) with a relatively small human budget.
  arXiv  Detail & Related papers  (2021-11-17T05:00:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.