魔术、疯狂、天堂、罪恶：LLM输出多样性无处不在
Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once
AI总结：
本文提出Magic, Madness, Heaven, Sin框架，从四个规范性场景分析LLM输出多样性，揭示任务目标对输出多样性的影响，强调需基于任务目标进行多样性评估。
摘要：
针对大型语言模型（LLM）输出多样性研究，本文探讨生成、推理、对齐和表征分析中的输出变化，通常统称为“多样性”。然而术语碎片化，因任务的规范性目标常未明确。我们引入Magic, Madness, Heaven, Sin框架，沿同质性-异质性轴度量输出变化，估值由任务及其规范性目标决定。将任务分为四个规范性场景：认知（事实性）、互动（用户效用）、社会（表征）和安全（鲁棒性）。对每个场景，分析失败模式和词汇如幻觉、模式崩溃、偏见和擦除。将框架应用于分析所有跨场景交互，揭示优化一个目标如提高安全性可能无意损害人口表征或创造性多样性。我们主张基于任务目标的输出多样性评估，将其视为由任务目标塑造的属性，而非模型固有特性。
英文摘要：
Research on Large Language Models (LLMs) studies output variation across generation, reasoning, alignment, and representational analysis, often under the umbrella of "diversity." Yet the terminology remains fragmented, largely because the normative objectives underlying tasks are rarely made explicit. We introduce the Magic, Madness, Heaven, Sin framework, which models output variation along a homogeneity-heterogeneity axis, where valuation is determined by the task and its normative objective. We organize tasks into four normative contexts: epistemic (factuality), interactional (user utility), societal (representation), and safety (robustness). For each, we examine the failure modes and vocabulary such as hallucination, mode collapse, bias, and erasure through which variation is studied. We apply the framework to analyze all pairwise cross-contextual interactions, revealing that optimizing for one objective, such as improving safety, can inadvertently harm demographic representation or creative diversity. We argue for context-aware evaluation of output variation, reframing it as a property shaped by task objectives rather than a model's intrinsic trait.
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。
