面向大语言模型部署的免调优可问责干预——一种元认知方法
Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
AI总结：
针对大语言模型黑箱幻觉、高风险场景下不可问责的问题，提出元认知方法CLEAR，通过构建概念稀疏子网络实现免调优的自识别纠错与可解释干预，提升模型部署可信度。
摘要：
大语言模型（LLM）通过少样本或零样本提示，在各类自然语言处理任务中实现了变革性进展，无需参数调优。这种模式虽便捷，却加剧了“幻觉”问题，尤其是其庞大模型规模背后神秘的“黑箱”特性更令问题凸显。在医疗等高风险应用中，不可问责的决策错误会造成毁灭性后果，此类担忧进一步加剧。相比之下，人类决策依赖精细的认知过程，比如通过概念理解感知并自适应纠正误判的能力。受人类认知启发，我们提出一种创新的元认知方法，名为CLEAR，赋予LLM自我感知错误识别与纠正的能力。我们的框架支持构建特定概念的稀疏子网络，展现透明的决策路径，为部署后的模型干预提供了全新接口。我们的干预方法具备显著优势：（i）在部署或推理阶段，我们的元认知LLM能以最少的人工参与，自主识别潜在的错误预测；（ii）模型能够高效自我纠正错误，无需额外调优；（iii）纠正过程不仅可自解释，还具备用户友好性，提升了模型的可解释性与易用性。通过整合这些元认知特性，我们的方法为提升LLM部署的可信度与可问责性开辟了新路径。
英文摘要：
Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks through few-shot or zero-shot prompting, bypassing the need for parameter tuning. While convenient, this modus operandi aggravates ``hallucination'' concerns, particularly given the enigmatic ``black-box'' nature behind their gigantic model sizes. Such concerns are exacerbated in high-stakes applications (e.g., healthcare), where unaccountable decision errors can lead to devastating consequences. In contrast, human decision-making relies on nuanced cognitive processes, such as the ability to sense and adaptively correct misjudgments through conceptual understanding. Drawing inspiration from human cognition, we propose an innovative \textit{metacognitive} approach, dubbed \textbf{CLEAR}, to equip LLMs with capabilities for self-aware error identification and correction. Our framework facilitates the construction of concept-specific sparse subnetworks that illuminate transparent decision pathways. This provides a novel interface for model \textit{intervention} after deployment. Our intervention offers compelling advantages: (\textit{i})~at deployment or inference time, our metacognitive LLMs can self-consciously identify potential mispredictions with minimum human involvement, (\textit{ii})~the model has the capability to self-correct its errors efficiently, obviating the need for additional tuning, and (\textit{iii})~the rectification procedure is not only self-explanatory but also user-friendly, enhancing the interpretability and accessibility of the model. By integrating these metacognitive features, our approach pioneers a new path toward engendering greater trustworthiness and accountability in the deployment of 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。
