arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.13751cs.CL
收藏

哪些模型在继承推理中表现更好?

Which Models Perform Better in Inheritance Reasoning?

Paris Dauphine University(巴黎多芬纳大学);University of Abou Bekr Belkaïd(阿布·贝克尔·贝尔卡伊德大学)

Mohammed Amine Mouhoub, Chahinez Bouchekif

AI总结:

本文比较了商业和开源大语言模型在伊斯兰继承推理任务中的表现,发现商业模型在识别继承人、应用排除规则和保持推理一致性方面更优,其中Gemini 2.5 Flash表现最佳。

摘要:

本文介绍了PSL团队在QIAS 2026阿拉伯伊斯兰继承推理共享任务中的参与情况。该任务评估大语言模型解决需要法律解释、多步推理和精确数值计算的继承案例的能力。我们在统一的提示策略下比较了\textit{商业}和\textit{开源}模型,以评估它们在最小任务特定适应下的结构化法律推理中的有效性。\我们的结果显示两个模型系列在可靠性上存在明显差距。商业模型在识别合格继承人、应用排除规则以及保持推理步骤一致性方面表现出更强的性能。相比之下,开源模型表现出更大的不稳定性,特别是在涉及依赖法律决策和分数份额调整的案例中。最佳性能由\textit{Gemini 2.5 Flash}实现,其MRE为$0.989$。

英文摘要:

This paper presents the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance reasoning. The task evaluates the ability of large language models to solve inheritance cases that require legal interpretation, multi-step reasoning, and precise numerical computation. We compare \textit{commercial} and \textit{open-source} models under a unified prompting strategy to assess their effectiveness in structured legal reasoning with minimal task-specific adaptation. \\ Our results show a clear gap in reliability between the two model families. Commercial models demonstrate stronger performance in identifying eligible heirs, applying exclusion rules, and maintaining consistency across reasoning steps. In contrast, open-source models exhibit greater instability, particularly in cases involving dependent legal decisions and fractional share adjustments. The best performance is achieved by \textit{Gemini 2.5 Flash}, with an MRE of $0.989$.

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。

↑