JudgeMeNot: 为 Hebrew 语境下的司法推理个性化大型语言模型
JudgeMeNot: Personalizing Large Language Models to Emulate Judicial Reasoning in Hebrew
AI总结：
本文提出一种合成有机监督流程，通过将原始司法判决转化为指令微调数据，实现低资源环境下对法官个性化模型的高效微调，并在三个任务中验证了因果语言模型结合合成指令微调的优越性。
摘要：
尽管大型语言模型取得了显著进展，但为其个体决策者进行个性化仍是一个开放性问题。本文介绍了一种合成-有机监督流程，将原始司法判决转化为指令微调数据，从而在低资源环境下实现对个体法官的参数高效微调。我们跨三个不同任务和设置比较了我们的方法与最先进的个性化技术。结果表明，因果语言模型结合合成生成的指令微调显著优于所有其他基线，提供了在词汇、风格和语义相似性方面的显著改进。值得注意的是，我们的模型生成输出与人类法官的推理无差异，凸显了在低资源环境下高效个性化方案的可行性。
英文摘要：
Despite significant advances in large language models, personalizing them for individual decision-makers remains an open problem. Here, we introduce a synthetic-organic supervision pipeline that transforms raw judicial decisions into instruction-tuning data, enabling parameter-efficient fine-tuning of personalized models for individual judges in low-resource settings. We compare our approach to state-of-the-art personalization techniques across three different tasks and settings. The results show that Causal Language Modeling followed by synthetically generated instruction-tuning significantly outperforms all other baselines, providing significant improvements across lexical, stylistic, and semantic similarity. Notably, our model-generated outputs are indistinguishable from the reasoning of human judges, highlighting the viability of efficient personalization, even in low-resource settings.
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。
