PILOT：以心理与语言输出目标引导合成数据生成
PILOT: Steering Synthetic Data Generation with Psychological & Linguistic Output Targeting
AI总结：
PILOT框架通过将自然语言画像转换为结构化心理语言学画像来引导大语言模型生成合成数据，实验表明基于模式的方法能显著减少画像重复并提高输出连贯性，混合引导则在多样性与一致性之间取得平衡。
摘要：
生成式人工智能应用通常利用用户画像作为合成数据生成的引导机制，但对自然语言表示的依赖迫使模型对应当强调哪些属性做出非预期推断，限制了对输出的精确控制。我们提出PILOT（Psychological and Linguistic Output Targeting，心理与语言输出目标引导），一个利用结构化心理语言学画像引导大语言模型的两阶段框架。在第一阶段，PILOT将自然语言画像描述转换为多维画像，并在语言维度和心理维度上给出归一化分数。在第二阶段，这些画像沿着可测量的变异轴引导生成。我们在三个最先进的大语言模型（Mistral Large 2、Deepseek-R1、LLaMA 3.3 70B）上，使用25个合成画像，在三种条件下评估PILOT：自然语言画像引导（NPS）、基于模式的引导（SBS）以及混合画像-模式引导（HPS）。结果表明，基于模式的方法显著减少了听起来不自然的画像重复，同时提高了输出连贯性，轮廓系数从0.098提高到0.237，主题纯度从0.773提高到0.957。我们的分析揭示了一个基本权衡：SBS产生更简洁的输出并具有更高的主题一致性，而NPS提供更大的词汇多样性但可预测性较低。HPS在这些极端之间取得平衡，在保持结构一致性的同时维持输出多样性。专家语言评估证实，PILOT在所有条件下都保持了较高的回答质量，不同引导方法之间没有统计学显著差异。
英文摘要：
Generative AI applications commonly leverage user personas as a steering mechanism for synthetic data generation, but reliance on natural language representations forces models to make unintended inferences about which attributes to emphasize, limiting precise control over outputs. We introduce PILOT (Psychological and Linguistic Output Targeting), a two-phase framework for steering large language models with structured psycholinguistic profiles. In Phase 1, PILOT translates natural language persona descriptions into multidimensional profiles with normalized scores across linguistic and psychological dimensions. In Phase 2, these profiles guide generation along measurable axes of variation. We evaluate PILOT across three state-of-the-art LLMs (Mistral Large 2, Deepseek-R1, LLaMA 3.3 70B) using 25 synthetic personas under three conditions: Natural-language Persona Steering (NPS), Schema-Based Steering (SBS), and Hybrid Persona-Schema Steering (HPS). Results demonstrate that schema-based approaches significantly reduce artificial-sounding persona repetition while improving output coherence, with silhouette scores increasing from 0.098 to 0.237 and topic purity from 0.773 to 0.957. Our analysis reveals a fundamental trade-off: SBS produces more concise outputs with higher topical consistency, while NPS offers greater lexical diversity but reduced predictability. HPS achieves a balance between these extremes, maintaining output variety while preserving structural consistency. Expert linguistic evaluation confirms that PILOT maintains high response quality across all conditions, with no statistically significant differences between steering approaches.
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。
