用语言模型生成对话选项，发现减少意外感最能预测说话人选择。
Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue
- 基于语言模型生成目标相关与上下文合理两种对话选项
- 在多种条件下，最小化对目标选项的意外感预测力最强
- 适合研究自然对话中说话人和听话人压力机制
我们将话语生成建模为在上下文选项中进行概率性、成本敏感的选择，采用信息论的成本概念。区分实现固定交际意图的目标导向选项与仅由上下文合理性定义的目标无关选项，从而推导出说话人与听话人导向的不同成本度量解释。我们提出一种使用语言模型生成两类选项集的方法。在开放对话中分析确定性和概率性成本最小化下的生成选择，发现相对于目标导向选项的意外感最小化在两种分析中均提供最强预测效果。相比之下，均匀信息密度和长度成本表现出较弱且不一致的预测能力。更广泛而言，我们的研究表明，以选项为条件的语言模型优化框架，为研究自然语言生成中的说话人与听话人压力提供了原则性基础。
原文摘要 · Abstract (English)
We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost. We distinguish between goal-directed alternatives that realise a fixed communicative intent and goal-agnostic alternatives defined only by contextual plausibility, allowing us to derive speaker- and listener-oriented interpretations of different cost measures. We present a procedure to generate both types of alternative sets using language models. Analysing production choices in open-ended dialogue under both deterministic and probabilistic cost minimisation, we find that surprisal minimisation relative to goal-directed alternatives provides the strongest predictive account under both analyses. By contrast, uniform information density and length-based costs exhibit weaker and less consistent predictive power across conditions. More broadly, our study suggests that alternative-conditioned optimisation with LM-generated alternatives provides a principled framework for studying speaker and listener pressures in naturalistic language production.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。