将对话摩擦视为构建共识的关键信号，拓展至信息不对称场景。
From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue
- 将对话摩擦从命题不对称扩展到感知不对称，考虑信息局部差异。
- 发现少数模糊场景导致大量误解，且单方知情比全知更有效。
- 提出新标注方式，提升对认知错位的识别能力，适合对话系统研究者。
Frictive Policy Optimization（FPO；Pustejovsky et al., 2025）将协作对话中的摩擦——如分歧、误解、修正——视为共同认知构建的关键认知信号，而非需消除的噪声。然而，现有FPO假设共享感知语境，摩擦源于对同一场景的不同命题理解，即命题不对称。本文将其拓展至感知不对称：参与者拥有不对称的部分信息，同一指称表达在不同信息状态中指向不同实体。通过跨语料库分析与大模型探测，在以HCRC MapTask（Anderson et al., 1991）为代表的指称不对称对话任务上验证。结果表明，仅当从各参与者的认知视域内评估时，FPO的摩擦函数才具实证有效性：不同地标配置引发质异的对接失败模式，少量模糊配置驱动了不成比例的误解，其路径看似成功却悄然偏离。大模型探测进一步确认，具备‘正确视角’比掌握所有视角更重要——单一知情视角优于同时访问双方上下文的全知状态。本文提出两项标注改进：待定对接状态的子类型分解，以及考虑适应性的对齐分类。
原文摘要 · Abstract (English)
Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as an epistemic signal essential to common-ground construction, rather than noise to be minimized. However, FPO and its implementations assume shared perceptual contexts, where friction arises from differently interpreted propositions over the same scene, which we define as propositional asymmetry. We extend FPO to perceptual asymmetry, where participants hold asymmetric partial information and the same referring expression yields different denotations depending on whose information state grounds the reference. We evaluate this through cross-corpora analysis and LLM probing on referentially asymmetric dialogue tasks, primarily the HCRC MapTask (Anderson et al., 1991). We find that FPO's friction functional is empirically valid only when evaluated from within each participant's information horizon: different landmark configurations produce qualitatively distinct grounding failure modes, with a small class of ambiguous configurations driving a disproportionate share of misunderstandings through trajectories that appear successful but silently diverge. The LLM probe confirms that having the "right perspective" matters more than having all perspectives: the informed single viewpoint outperforms omniscient access to both participants' contexts. We propose two annotation refinements: subtype decomposition of pending grounding states and accommodation-aware alignment classification.
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。