FReM：一种用于长上下文问答中平衡快速与慢速思考的灵活推理机制
FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering
AI总结：
针对长上下文问答中慢速思考过度探索和快速思考依赖模式匹配的问题，提出FReM灵活推理机制，利用合成参考示例提供思维链，按问题复杂度调整推理深度，在七个数据集上提升准确性和可扩展性。
摘要：
长上下文问答（LCQA）系统已从大型语言模型（LLMs）强大的推理能力中受益匪浅，这些能力可分为慢速和快速推理模式。然而，这两种模式都有其局限性。慢速思考通常倾向于探索每一条可能的推理路径，这导致严重的过度思考并浪费时间。快速思考通常依赖模式匹配而非真正理解查询逻辑，从而缺乏正确的理解。为解决这些问题，我们提出了FReM：灵活推理机制，一种根据每个问题的复杂度调整推理深度的方法。具体而言，FReM利用合成的参考问答示例来提供显式的思维链，从而能够高效处理简单查询，同时允许对更复杂的查询进行更深层次的推理。通过这种方式，FReM帮助快速思考模型超越表面模式匹配，并缩小慢速思考模型的推理空间以避免不必要的探索。在七个问答数据集上的实验表明，FReM提高了推理准确性和可扩展性，特别是在复杂的多跳问题上，表明其推进LCQA方法的潜力。
英文摘要：
Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their limitations. Slow thinking generally leans to explore every possible reasoning path, which leads to heavy overthinking and wastes time. Quick thinking usually relies on pattern matching rather than truly understanding the query logic, which misses proper understanding. To address these issues, we propose FReM: Flexible Reasoning Mechanism, a method that adjusts reasoning depth according to the complexity of each question. Specifically, FReM leverages synthetic reference QA examples to provide an explicit chain of thought, enabling efficient handling of simple queries while allowing deeper reasoning for more complex ones. By doing so, FReM helps quick-thinking models move beyond superficial pattern matching and narrows the reasoning space for slow-thinking models to avoid unnecessary exploration. Experiments on seven QA datasets show that FReM improves reasoning accuracy and scalability, particularly for complex multihop questions, indicating its potential to advance LCQA methodologies.
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。
