迈向CausalGPT：通过提升LLM中的因果一致性实现忠实知识推理的多智能体方法
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
AI总结：
针对基础模型知识推理中存在的概念错误、推理谬误等问题，提出因果一致性思维链（CaCo-CoT）多智能体框架，通过推理器生成因果推理链、评估器从非因果和反事实视角审视因果一致性，在多任务上优于现有方法。
摘要：
尽管基础模型取得了进展，但基于知识的推理仍是一项持续挑战，原因在于其知识召回和推理能力有限。现有方法主要聚焦于鼓励这些模型规划和解决问题，或独立广泛采样推理链。然而，这些方法常忽视概念错误和推理谬误，不可避免地导致一系列突出问题，如误导性结论、认知偏差和决策质量下降。虽然明确建模因果关系被认为有望解决这些问题，但当代研究努力迄今未能实现基于因果关系的基础模型。受多种专业智能体协作解决复杂任务的启发，我们提出了一个名为因果一致性思维链（CaCo-CoT）的框架，该框架利用多智能体协作来增强基础模型的忠实性和因果性，涉及一组推理器和评估器。这些智能体在推理与共识范式内协作以提高忠实性。推理器的任务是通过模仿人类因果推理为知识密集型问题生成推理链。同时，评估器从非因果和反事实视角审视推理器推理链的因果一致性。我们的框架通过在基于文本和多模态知识推理任务（如科学问答和常识推理）上进行广泛全面的评估，展现出相较于最先进方法的显著优势。
英文摘要：
Despite the progress of foundation models, knowledge-based reasoning remains a persistent challenge due to their limited capacity for knowledge recall and inference. Existing methods primarily focus on encouraging these models to plan and solve problems or extensively sample reasoning chains independently. However, these methods often overlook conceptual errors and inferential fallacies, inevitably leading to a series of notorious issues such as misleading conclusions, cognitive biases, and reduced decision quality. While explicit modeling of causality is argued to hold promise in addressing these issues, contemporary research efforts have thus far fallen short in achieving causality-based foundation models. Drawing inspiration from the orchestration of diverse specialized agents collaborating to tackle intricate tasks, we propose a framework named Causal-Consistency Chain-of-Thought (CaCo-CoT) that harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models, involving a set of reasoners and evaluators. These agents collaboratively work within a reasoning-and-consensus paradigm to improve faithfulness. The reasoners are tasked with generating reasoning chains for knowledge-intensive problems by mimicking human causal reasoning. Meanwhile, the evaluator scrutinizes the causal consistency of a reasoner's reasoning chain from a non-causal and a counterfactual perspective. Our framework demonstrates significant superiority over state-of-the-art methods through extensive and comprehensive evaluations across text-based and multi-modal knowledge reasoning tasks (e.g., science question answering and commonsense reasoning).
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。
