Scattered Hypothesis Generation for Open-Ended Event Forecasting

2026-04-17

AI Summary

This work addresses the limitation of current large language models in open-ended event prediction, which typically focus solely on the most probable outcome while neglecting the inherent uncertainty of future events. To overcome this, the authors propose SCATTER (Scatter Prediction), a novel paradigm that leverages a hypothesis generation task to explore diverse yet plausible future scenarios. They introduce a reinforcement learning–based framework that jointly optimizes the validity of generated hypotheses alongside intra- and inter-group diversity. A hybrid reward mechanism combined with a validity gating module ensures semantic plausibility while effectively mitigating mode collapse. Experimental results demonstrate that SCATTER significantly outperforms strong baselines on two real-world benchmarks, OpenForecast and OpenEP.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Despite the importance of open-ended event forecasting for risk management, current LLM-based methods predominantly target only the most probable outcomes, neglecting the intrinsic uncertainty of real-world events. To bridge this gap, we advance open-ended event forecasting from pinpoint forecasting to scatter forecasting by introducing the proxy task of hypothesis generation. This paradigm aims to generate an inclusive and diverse set of hypotheses that broadly cover the space of plausible future events. To this end, we propose SCATTER, a reinforcement learning framework that jointly optimizes inclusiveness and diversity of the hypothesis. Specifically, we design a novel hybrid reward that consists of three components: 1) a validity reward that measures semantic alignment with observed events, 2) an intra-group diversity reward to encourage variation within sampled responses, and 3) an inter-group diversity reward to promote exploration across distinct modes. By integrating the validity-gated score into the overall objective, we confine the exploration of wildly diversified outcomes to contextually plausible futures, preventing the mode collapse issue. Experiments on two real-world benchmark datasets, i.e., OpenForecast and OpenEP, demonstrate that SCATTER significantly outperforms strong baselines. Our code is available at https://github.com/Sambac1/SCATTER.

Problem

• open-ended event forecasting
• intrinsic uncertainty
• hypothesis generation
• diversity
• plausible futures

Innovation

• Scatter Forecasting
• Hypothesis Generation
• Reinforcement Learning
• Diversity Reward
• Open-Ended Event Forecasting