AURA：面向大型语言模型的供用性理解与风险感知对齐技术
AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
AI总结：
针对LLM因忽略逻辑含义而引发供用性安全风险的问题，提出多层框架AURA，结合内省自我批评、细粒度PRM评估与自适应安全感知解码，显著提升模型输出的逻辑完整性与安全性。
摘要：
当前的LLM面临管理基于供用性的安全风险的挑战，即由于忽略逻辑含义，输出无意中促进有害行为的情况。传统安全解决方案，如基于标量结果的奖励模型、参数调整或启发式解码策略，缺乏在微妙但关键的推理步骤中可靠检测和干预所需的粒度和主动性。针对这一根本差距，我们引入了AURA，这是一个以过程奖励模型（PRMs）为中心的创新多层框架，提供跨逻辑连贯性和安全感知的全面步骤级评估。我们的框架无缝结合了内省式自我批评、细粒度PRM评估和自适应安全感知解码，以动态且主动地引导模型走向更安全的推理轨迹。经验证据清楚地表明，该方法显著超越现有方法，大幅提升了模型输出的逻辑完整性和供用性敏感安全。这项研究是迈向更安全、更负责任和上下文感知AI的关键一步，为对齐敏感应用设定了新基准。
英文摘要：
Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar outcome-based reward models, parameter tuning, or heuristic decoding strategies, lack the granularity and proactive nature needed to reliably detect and intervene during subtle yet crucial reasoning steps. Addressing this fundamental gap, we introduce AURA, an innovative, multi-layered framework centered around Process Reward Models (PRMs), providing comprehensive, step level evaluations across logical coherence and safety-awareness. Our framework seamlessly combines introspective self-critique, fine-grained PRM assessments, and adaptive safety-aware decoding to dynamically and proactively guide models toward safer reasoning trajectories. Empirical evidence clearly demonstrates that this approach significantly surpasses existing methods, significantly improving the logical integrity and affordance-sensitive safety of model outputs. This research represents a pivotal step toward safer, more responsible, and contextually aware AI, setting a new benchmark for alignment-sensitive applications.
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。
