Scattered Hypothesis Generation for Open-Ended Event Forecasting

TL;DR

This paper introduces SCATTER, a reinforcement learning framework for open-ended event forecasting that generates diverse, plausible future hypotheses, addressing the limitations of current methods focused only on most probable outcomes.

Contribution

The paper proposes a novel hypothesis generation paradigm and a hybrid reward-based RL method to improve diversity and inclusiveness in open-ended event forecasting.

Findings

SCATTER outperforms strong baselines on benchmark datasets.

The hybrid reward effectively balances validity and diversity.

The approach prevents mode collapse by constraining exploration to plausible futures.

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.