发表机构
Hithink research; Nanyang Technological University（海天瑞声研究; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CHAIN通过分解因果-时序超图预测为三阶段并设计各阶段特定机制，缓解LLM概率输出的校准偏差，在跨领域基准上优于现有方法。
AI 中文摘要
大型语言模型在事件预测方面取得了显著进展，但其概率输出表现出系统性校准偏差，且该偏差在不同领域和问题类型间存在异质性，这削弱了在不确定性下进行决策时概率输出的可信度。然而，现有校准方法通常在预测完成后才修正概率输出，未对预测过程本身的结构性偏差来源进行建模。为解决这一挑战，我们将因果-时序超图上的概率预测分解为三个阶段：证据加权、证据聚合和来源融合，并提出CHAIN，该方法设计了各阶段特定的机制以缓解每个阶段的偏差：(i) 通过因果拓扑距离调节时间衰减函数，(ii) 在方向感知去重后通过Noisy-OR聚合近似独立的因果链，以及(iii) 通过因果覆盖率和方向平衡驱动自适应融合。跨领域预测基准上的实验结果表明，CHAIN在期望校准误差、Brier分数和准确性方面优于现有方法。我们的项目可在以下网址获取：此https URL。
英文摘要
Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that varies heterogeneously across different domains and question types, undermining the trustworthiness of probabilistic outputs for decision-making under uncertainty. However, existing calibration methods typically correct probability outputs after prediction is complete, without modeling the structural sources of bias within the prediction process itself. To address this challenge, we decompose probabilistic prediction over causal-temporal hypergraphs into three stages, evidence weighting, evidence aggregation, and source fusion, and propose CHAIN, which designs stage-specific mechanisms to mitigate bias at each stage: (i) modulating the temporal decay function by causal topological distance, (ii) aggregating approximately independent causal chains via Noisy-OR after direction-aware deduplication, and (iii) driving adaptive fusion by causal coverage and directional balance. Experimental results on cross-domain forecasting benchmarks show CHAIN outperforms existing methods in expected calibration error, Brier score, and accuracy. Our project is available at https://github.com/QwenQKing/Chain.
