诊断语言模型中的道德推理习得：语用学与泛化
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
AI总结：
本研究探讨当前学习范式能否让大语言模型获得足够道德推理能力，借鉴分布语义学与道德话语语用性质，发现性能提升受话语中隐含道德语用影响，提出“语用困境”现象，并指出其限制泛化能力，成为道德推理习得的主要瓶颈。
摘要：
确保大型语言模型（LLMs）返回符合社会价值观的公正回应，对其更广泛的应用至关重要。先前的研究表明，LLMs 在需要道德认知的任务（如基于伦理的判断）上往往表现不佳。虽然当前的方法侧重于使用精选数据集对 LLMs 进行微调，以提高其在此类任务上的能力，但选择最优的学习范式来增强 LLMs 的伦理回应仍然是一个开放的研究争论。在这项工作中，我们旨在解决这个基本问题：当前的学习范式能否使 LLMs 获得足够的道德推理能力？借鉴分布语义学理论和道德话语的语用性质，我们的分析表明，性能提升遵循与语义级任务相似的机制，因此仍然受到话语中隐含的道德语用性质的影响，我们将这一现象命名为“语用困境”。我们得出结论，这种语用困境对当前学习范式的泛化能力施加了显著限制，使其成为 LLMs 道德推理习得的主要瓶颈。
英文摘要：
Ensuring that Large Language Models (LLMs) return just responses which adhere to societal values is crucial for their broader application. Prior research has shown that LLMs often fail to perform satisfactorily on tasks requiring moral cognizance, such as ethics-based judgments. While current approaches have focused on fine-tuning LLMs with curated datasets to improve their capabilities on such tasks, choosing the optimal learning paradigm to enhance the ethical responses of LLMs remains an open research debate. In this work, we aim to address this fundamental question: can current learning paradigms enable LLMs to acquire sufficient moral reasoning capabilities? Drawing from distributional semantics theory and the pragmatic nature of moral discourse, our analysis indicates that performance improvements follow a mechanism similar to that of semantic-level tasks, and therefore remain affected by the pragmatic nature of morals latent in discourse, a phenomenon we name the pragmatic dilemma. We conclude that this pragmatic dilemma imposes significant limitations on the generalization ability of current learning paradigms, making it the primary bottleneck for moral reasoning acquisition in LLMs.
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。
