mlsanityData to 7 Oct 2026

OpenEP: Open-Ended Future Event Prediction

arXiv 2408.06578 ↗First posted 13 Aug 2024cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Future event prediction (FEP) is a long-standing and crucial task in the world, as understanding the evolution of events enables early risk identification, informed decision-making, and strategic planning. Existing work typically treats event prediction as classification tasks and confines the outcomes of future events to a fixed scope, such as yes/no questions, candidate set, and taxonomy, which is difficult to include all possible outcomes of future events. In this paper, we introduce OpenEP (an Open-Ended Future Event Prediction task), which generates flexible and diverse predictions aligned with real-world scenarios. This is mainly reflected in two aspects: firstly, the predictive questions are diverse, covering different stages of event development and perspectives; secondly, the outcomes are flexible, without constraints on scope or format. To facilitate the study of this task, we construct OpenEPBench, an open-ended future event prediction dataset. For question construction, we pose questions from seven perspectives, including location, time, event development, event outcome, event impact, event response, and other, to facilitate an in-depth analysis and understanding of the comprehensive evolution of events. For outcome construction, we collect free-form text containing the outcomes as ground truth to provide semantically complete and detail-enriched outcomes. Furthermore, we propose StkFEP, a stakeholder-enhanced future event prediction framework, that incorporates event characteristics for open-ended settings. Our method extracts stakeholders involved in events to extend questions to gather diverse information. We also collect historically events that are relevant and similar to the question to reveal potential evolutionary patterns. Experiment results indicate that accurately predicting future events in open-ended settings is challenging for existing LLMs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 30 of its 78 references that are in the map. First posted on arXiv 13 Aug 2024.

Builds on

30 of 78 references.

References · 30

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  5. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  6. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  7. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  8. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  9. 2021Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learningcited by 106
  10. 2023Why think step by step? Reasoning emerges from the locality of experiencecited by 103
  11. 2024Approaching Human-Level Forecasting with Language Modelscited by 102
  12. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
18 more
  1. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
  2. 2022Forecasting Future World Events with Neural Networkscited by 63
  3. 2024MIRAI: Evaluating LLM Agents for Event Forecastingcited by 40
  4. 2021The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Predictioncited by 39
  5. 2023Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournamentcited by 24
  6. 2023TEILP: Time Prediction over Knowledge Graphs via Logical Reasoningcited by 23
  7. 2024Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfercited by 19
  8. 2024Large Language Models as Evaluators for Recommendation Explanationscited by 19
  9. 2023AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrievalcited by 18
  10. 2024Can Language Models Use Forecasting Strategies?cited by 13
  11. 2023Context-aware Event Forecasting via Graph Disentanglementcited by 10
  12. 2022A Generative Approach for Script Event Prediction via Contrastive Fine-tuningcited by 9
  13. 2024A Comprehensive Evaluation of Large Language Models on Temporal Event Forecastingcited by 7
  14. 2022Rich Event Modeling for Script Event Predictioncited by 3
  15. 2024TacoERE: Cluster-aware Compression for Event Relation Extractioncited by 2
  16. 2021Causal Knowledge Guided Societal Event Forecastingcited by 1
  17. 2024Event GDR: Event-Centric Generative Document Retrievalcited by 1
  18. 2024From Text to Context: An Entailment Approach for News Stakeholder Classificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025FutureX: An Advanced Live Benchmark for LLM Agents in Future Predictioncited by 55
  2. 2025LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arenacited by 36
  3. 2025Scaling Open-Ended Reasoning to Predict the Futurecited by 19
  4. 2026Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefscited by 9
  5. 2025PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimationcited by 8
  6. 2025Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impactscited by 6
  7. 2025CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrencycited by 5
  8. 2026Decentralized Aggregation of LLM Predictions via Wagering Mechanismscited by 0
  9. 2026From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Modelscited by 0
  10. 2026Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecastscited by 0
  11. 2026CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inferencecited by 0