Lune

EMNLP Findings2025

ForestCast: Open-Ended Event Forecasting with Semantic News Forest

Zi Yu, Shaoxiang Wang, Guozheng Li, Yu Zhang, Chi Harold Liu

Abstract

Open-ended event forecasting (OEEF) seeks to predict future events from a given context without being restricted to a predefined scope or format. It plays a crucial role in domains such as risk management and financial decision making. Although large language models show potential for OEEF, existing approaches and datasets often overlook the complex relationships among events, and current research lacks comprehensive evaluation methods. To address these limitations, we propose ForestCast, a prediction pipeline that extracts forecast-relevant events from news data, organizes them into a story tree, and predicts subsequent events along each path. The pipeline comprises four steps: (1) clustering news into event nodes, (2) constructing a news story tree, (3) mining the semantic structure of the tree, and (4) predicting the next event node and evaluating prediction quality. To support this pipeline, we construct NewsForest, a dataset of 12,406 event chains, each representing a chronologically and logically linked sequence of news events. In addition, we introduce a comprehensive evaluation framework that measures both the accuracy and the quality of prediction. Experimental results demonstrate that ForestCast improves the ability of LLMs to forecast events in news data.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning cites Dynamic Knowledge Graph based Multi-Event Forecasting
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
  2. MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained TransformersWenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong et al.ACL Findings 2021 · 260 citations
  3. Dynamic Knowledge Graph based Multi-Event ForecastingSonggaojun Deng, Huzefa Rangwala, Yue NingKDD 2020 · 97 citations
  4. Language Models Can Improve Event Prediction by Few-Shot Abductive ReasoningXiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou et al.NeurIPS 2023 · 95 citations
  5. Pre-trained Language Model with Prompts for Temporal Knowledge Graph CompletionWenjie Xu, Ben Liu, Miao Peng, Xu Jia et al.ACL Findings 2023 · 53 citations

Related papers

  1. ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text DataWoojeong Jin, Rahul Khanna, Suji Kim, Dong-Ho Lee et al.ACL 2021
  2. Curating the Future: A Scalable Recipe for Training Open-Ended ForecastersNikhil Chandak, Shashwat Goel, Ameya Pandurang Prabhu, Moritz Hardt et al.ICML 2026
  3. AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context RetrievalQi Yan, Raihan Seraj, Jiawei He, Lili Meng et al.ICLR 2024 · 15 citations
  4. Event-Driven Learning of Systematic Behaviours in Stock MarketsXianchao WuEMNLP Findings 2020 · 7 citations
  5. REST: Relational Event-driven Stock Trend ForecastingWentao Xu, Weiqing Liu, Chang Xu, Jiang Bian et al.WWW 2021 · 76 citations
Dusk over the sea between two cliffs drawn in fine vertical lines