Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisions. We study whether large language models (LLMs) can learn and reproduce such annotator-specific label-explanation behavior. Using two sentence-pair tasks with four annotators each -- natural language inference and paraphrase judgment -- we first analyze whether annotators exhibit stable individual patterns. We find that such patterns are weak at the single-annotation level due to strong input-content effects, but become detectable after input-content reduction and annotator-level aggregation. We then compare prompting and supervised fine-tuning (SFT) baselines and propose cross-annotator preference optimization (CAPO), which contrasts a target annotator's response with other valid but less target-specific annotations for the same input. Experiments show that prompting is limited and unstable, SFT better captures annotator-specific behavior, and CAPO further improves aggregation-aware imitation and judge-based attribution while preserving target-specific reasoning patterns under human validation. Overall, our results show that HLV can be learned as annotator-specific label-explanation behavior, suggesting a path toward scalable explanation-based annotation grounded in annotator histories rather than labels alone.

翻译：自由文本解释通过揭示标注者决策背后的推理和偏好，将人类标注变异从标签不一致扩展到了更深层面。我们研究大语言模型是否能够学习并复现这种标注者特定的标签-解释行为。使用两个句子对任务（自然语言推理和释义判断）各含四名标注者，我们首先分析标注者是否表现出稳定的个体模式。研究发现，由于输入内容的强烈影响，单次标注层面的模式较弱，但在降低输入内容影响并进行标注者层面聚合后变得可检测。随后，我们比较了提示学习和监督微调基线，并提出跨标注者偏好优化方法，该方法将目标标注者的响应与同一输入的其他有效但非目标特定标注进行对比。实验表明，提示学习效果有限且不稳定，监督微调能更好捕捉标注者特定行为，而跨标注者偏好优化在人类验证下，进一步提升了聚合感知模仿和基于判断的归因能力，同时保留了目标特定的推理模式。总体而言，我们的结果表明，人类标注变异可作为标注者特定的标签-解释行为被学习，这为实现基于解释的可扩展标注（以标注者历史为基础而非仅依赖标签）提供了可能路径。