模型编辑是一把双刃剑：引导智能体伦理行为走向向善或致害
Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
AI总结：
本文将智能体伦理行为引导建模为Behavior Editing任务，构建多层级基准BehaviorBench，验证该方法可局部或全局调整智能体道德对齐，既能引导向善也能诱导作恶，揭示其双面性。
摘要：
基于大语言模型（LLM）的智能体已在各类任务中展现出强大能力，但在高风险领域部署这类智能体存在显著的安全与伦理风险，其不道德行为会直接造成人身伤害、经济损失等严重现实后果。为高效引导智能体的伦理行为，我们将智能体行为引导建模为一项模型编辑任务，将其命名为Behavior Editing（行为编辑）。模型编辑是新兴研究方向，可在保留LLM整体能力的前提下对其进行精准高效的修改。为系统研究并评估该方法，我们推出基于心理学道德理论构建的多层级基准BehaviorBench，该基准支持多场景下的智能体行为评估与编辑，每一层级都设置了更复杂、模糊的场景。我们首先证明，行为编辑可在特定场景内动态引导智能体做出目标行为；此外，它不仅能实现场景特定的局部调整，还能引发智能体全局道德对齐的更广泛偏移。我们证实，行为编辑既可以用来推动智能体做出符合伦理的善意行为，反过来也能诱导其做出有害的恶意行为。通过对基于前沿LLM构建的智能体开展大量评估，BehaviorBench验证了行为编辑在各类模型和场景下的有效性。我们的研究发现为智能体行为引导的新范式提供了关键洞见，同时凸显了行为编辑的应用前景与潜在风险。
英文摘要：
Agents based on Large Language Models (LLMs) have demonstrated strong capabilities across a wide range of tasks. However, deploying LLM-based agents in high-stakes domains comes with significant safety and ethical risks. Unethical behavior by these agents can directly result in serious real-world consequences, including physical harm and financial loss. To efficiently steer the ethical behavior of agents, we frame agent behavior steering as a model editing task, which we term Behavior Editing. Model editing is an emerging area of research that enables precise and efficient modifications to LLMs while preserving their overall capabilities. To systematically study and evaluate this approach, we introduce BehaviorBench, a multi-tier benchmark grounded in psychological moral theories. This benchmark supports both the evaluation and editing of agent behaviors across a variety of scenarios, with each tier introducing more complex and ambiguous scenarios. We first demonstrate that Behavior Editing can dynamically steer agents toward the target behavior within specific scenarios. Moreover, Behavior Editing enables not only scenario-specific local adjustments but also more extensive shifts in an agent's global moral alignment. We demonstrate that Behavior Editing can be used to promote ethical and benevolent behavior or, conversely, to induce harmful or malicious behavior. Through extensive evaluations of agents built on frontier LLMs, BehaviorBench validates the effectiveness of behavior editing across a wide range of models and scenarios. Our findings offer key insights into a new paradigm for steering agent behavior, highlighting both the promise and perils of Behavior Editing.
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。
