六头 llama：通过 LoRA 调整的语言模型进行比较宗教伦理研究
Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models
AI总结：
本文通过 LoRA 调整的语言模型比较不同宗教文本对伦理推理的影响，发现调整模型在伦理推理上与基础模型有系统性差异，并在不同温度设置下表现出稳定性与多样性。
摘要：
我们提出了 Six Llamas，一项比较研究，探讨是否通过在不同宗教语料库上微调的大语言模型会系统性地表现出不同的伦理推理模式。六种 Meta-Llama-3.1-8B 的变体被构建：一个未修改的对照模型和五个通过 LoRA 调整的模型，分别在基督教、伊斯兰教、犹太教、印度教或佛教的神圣和神学文本上训练。所有六个模型都使用相同的 17 个标准化伦理提示进行测试，涵盖道德困境、博弈论情境、公共政策问题和道德心理自我评估。为了评估鲁棒性和可重复性，我们实现了一个跨越十个温度设置的多温度采样设计。我们计算了响应一致性度量、模型间配对一致性率、四个提示领域中的温度敏感性系数，以及运行间稳定性分析。研究发现，LoRA 调整的模型产生的伦理推理模式在 (a) 系统性地与基础模型不同， (b) 与训练传统中的道德逻辑一致， (c) 在道德哲学空间中沿着可解释的维度结构化， (d) 在高共识困境中核心伦理立场在温度变化下保持稳定。电车问题在所有模型和温度下达到 100% 一致性，而 (e) 传统特定的分歧在道德争议领域中在更高温度下加剧， (f) 基础模型表现出最高的总体响应一致性（均值 88.3%），表明 LoRA 调整引入了传统特定的信号和增加的采样敏感性。本研究为使用差异训练语言模型作为文化与伦理分析工具的浓缩比较方法提供了概念验证，并确定了特定的可证伪性标准和计划扩展。
英文摘要：
We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Six variants of Meta-Llama-3.1-8B are constructed: one unmodified control and five LoRA-adapted models trained exclusively on the sacred and theological texts of Christianity, Islam, Judaism, Hinduism, or Buddhism. All six models are probed with an identical battery of 17 standardized ethical prompts spanning moral dilemmas, game-theoretic scenarios, public policy questions, and moral-psychological self-assessments. To assess robustness and reproducibility, we implement a multi-temperature sampling design spanning ten temperature settings. We compute response consistency metrics, pairwise inter-model agreement rates, temperature sensitivity coefficients across four prompt domains, and run-to-run stability analyses. Findings show that LoRA-adapted models produce ethical reasoning patterns that are (a) systematically differentiated from the base model, (b) consistent with the moral logics of their training traditions, (c) structured along interpretable dimensions in moral-philosophical space, (d) core ethical positions remain stable across temperature variations for high-consensus dilemmas. The Trolley Problem achieves 100% consistency across all models and temperatures, while (e) tradition-specific divergence intensifies at higher temperatures in morally contested domains, and (f) the base model exhibits the highest overall response consistency (mean 88.3%), suggesting LoRA adaptation introduces both tradition-specific signal and increased sampling sensitivity. The study offers a proof-of-concept for the condensate comparative method using differentially trained language models as instruments for cultural and ethical analysis and identifies specific criteria for falsification and planned extensions.
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。
