对主观分析中语言模型不确定性与人类分歧的对齐
Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
AI总结：
本文提出DPUA框架，通过感知分歧和对齐不确定性，提升模型在主观分析中的可靠性与泛化能力。
摘要：
用于主观分析的大型语言模型通常通过聚合标签进行训练，将人类判断的变异压缩成单一监督信号。这种范式忽视了低一致样本的内在不确定性，常导致过度自信的预测，损害复杂主观场景下的可靠性与泛化能力。本文倡导不确定性感知的主观分析，使模型在预测时表达反映人类分歧的不确定性。为此，我们提出一个两阶段的分歧感知与不确定性对齐（DPUA）框架。具体而言，DPUA在不确定性感知的设定下联合建模标签预测、推理生成和不确定性表达。在分歧感知阶段，自适应解耦学习增强了模型对分歧相关线索的敏感性，同时保持任务性能。在不确定性对齐阶段，基于GRPO的奖励优化进一步提升不确定性感知推理，并将模型置信度表达与人类分歧分布对齐。在三个主观分析任务上的实验表明，DPUA在保持任务性能的同时，更好地对齐了模型不确定性与人类分歧，缓解了边界样本上的过度自信，并提升了分布外泛化能力。
英文摘要：
Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This paradigm overlooks the intrinsic uncertainty of low-agreement samples and often induces overconfident predictions, undermining reliability and generalization in complex subjective settings. In this work, we advocate uncertainty-aware subjectivity analysis, where models are expected to make predictions while expressing uncertainty that reflects human disagreement. To operationalize this perspective, we propose a two-phase Disagreement Perception and Uncertainty Alignment (DPUA) framework. Specifically, DPUA jointly models label prediction, rationale generation, and uncertainty expression under an uncertainty-aware setting. In the disagreement perception phase, adaptive decoupled learning enhances the model's sensitivity to disagreement-related cues while preserving task performance. In the uncertainty alignment phase, GRPO-based reward optimization further improves uncertainty-aware reasoning and aligns the model's confidence expression with the human disagreement distribution. Experiments on three subjectivity analysis tasks show that DPUA preserves task performance while better aligning model uncertainty with human disagreement, mitigating overconfidence on boundary samples, and improving out-of-distribution generalization.
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。
