从字面到灵活：一种用于激发大型语言模型中人类对齐异常处理的元提示框架
From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models
AI总结：
针对LLMs规则僵化问题，提出低计算量元提示框架RID，通过结构化认知图式激发零样本人类对齐异常处理，在20场景基准上达到95%人类对齐分数，优于基线和CoT。
摘要：
大型语言模型（LLMs）正越来越多地被部署为智能体AI系统的推理引擎，然而它们表现出一个关键缺陷：对显式规则的僵化遵循，导致决策与人类常识和意图不一致。这种“规则僵化”是构建可信自主智能体的重大障碍。虽然先前的工作表明，使用人类解释进行监督微调（SFT）可以缓解这一问题，但SFT计算成本高昂，且对许多从业者而言难以触及。为弥补这一差距，我们引入了规则-意图区分（RID）框架，一种新颖的、低计算量的元提示技术，旨在以零样本方式激发LLMs中人类对齐的异常处理。RID框架为模型提供结构化的认知图式，用于解构任务、分类规则、权衡冲突结果并论证其最终决策。我们在一个包含20个跨不同领域需要细致判断的场景的自定义基准上，将RID框架与基线和思维链（CoT）提示进行了评估。我们经过人工验证的结果表明，RID框架显著提升了性能，达到了95%的人类对齐分数（HAS），而基线和CoT分别为80%和75%。此外，它持续产生更高质量、意图驱动的推理。这项工作提供了一种实用、可访问且有效的方法，引导LLMs从字面的指令遵循转向灵活的、目标导向的推理，为更可靠和务实的AI智能体铺平了道路。
英文摘要：
Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems, yet they exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense and intent. This "rule-rigidity" is a significant barrier to building trustworthy autonomous agents. While prior work has shown that supervised fine-tuning (SFT) with human explanations can mitigate this issue, SFT is computationally expensive and inaccessible to many practitioners. To address this gap, we introduce the Rule-Intent Distinction (RID) Framework, a novel, low-compute meta-prompting technique designed to elicit human-aligned exception handling in LLMs in a zero-shot manner. The RID framework provides the model with a structured cognitive schema for deconstructing tasks, classifying rules, weighing conflicting outcomes, and justifying its final decision. We evaluated the RID framework against baseline and Chain-of-Thought (CoT) prompting on a custom benchmark of 20 scenarios requiring nuanced judgment across diverse domains. Our human-verified results demonstrate that the RID framework significantly improves performance, achieving a 95% Human Alignment Score (HAS), compared to 80% for the baseline and 75% for CoT. Furthermore, it consistently produces higher-quality, intent-driven reasoning. This work presents a practical, accessible, and effective method for steering LLMs from literal instruction-following to liberal, goal-oriented reasoning, paving the way for more reliable and pragmatic AI agents.
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。
