论证连贯的判断性预测
Argumentatively Coherent Judgmental Forecasting
AI总结：
本文提出并定义论证连贯性性质，通过评估表明过滤不连贯预测可提升人类及LLM预测准确性，但用户对该性质认同度低，需在基于论证的判断性预测中整合过滤机制。
摘要：
判断性预测采用人类观点对未来事件进行预测，而非像定量预测那样完全依赖历史数据。当这些观点围绕预测形成论证结构时，从论证角度研究预测的性质十分有用。本文提出并正式定义了论证连贯性的性质，其本质要求预测者的推理与其预测保持一致。随后，我们基于这一连贯性概念开展了三项评估。首先，鉴于大型语言模型（LLM）预测者最近表现出与人类预测者相当的竞争力，我们评估了强制连贯性对人类预测者和基于LLM的预测者的影响。在两种情况下，我们均表明过滤掉不连贯的预测能持续提高预测准确性，证明连贯性在人类和基于LLM的预测中均具有实用价值。其次，通过众包用户实验，我们发现尽管连贯性看似直观且有用，但用户通常并不认同这一性质。这表明在基于论证的判断性预测中，需要整合相关机制，在获取群体预测结果前过滤掉不连贯的观点。
英文摘要：
Judgmental forecasting employs human opinions to make predictions about future events, rather than exclusively historical data as in quantitative forecasting. When these opinions form an argumentative structure around forecasts, it is useful to study the properties of the forecasts from an argumentative perspective. In this paper, we advocate and formally define a property of argumentative coherence, which, in essence, requires that a forecaster's reasoning is coherent with their forecast. We then conduct three evaluations with our notion of coherence. First, we assess the impact of enforcing coherence on human forecasters as well as on Large Language Model (LLM)-based forecasters, given that they have recently shown to be competitive with human forecasters. In both cases, we show that filtering out incoherent predictions improves forecasting accuracy consistently, supporting the practical value of coherence in both human and LLM-based forecasting. Then, via crowd-sourced user experiments, we show that, despite its apparent intuitiveness and usefulness, users do not generally align with this coherence property. This points to the need to integrate, within argumentation-based judgmental forecasting, mechanisms to filter out incoherent opinions before obtaining group forecasting predictions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
