FReM让问答模型智能调节推理深浅，提升复杂问题准确率。
FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering
- 根据问题难度动态调整推理深度，结合快慢思考优势。
- 在7个数据集上显著提升复杂多跳问题的准确率。
- 适合需要高效精准长文本推理的应用场景。
长上下文问答（LCQA）系统受益于大语言模型的强大推理能力，这些能力可分为快速和缓慢推理模式。然而，两者均有局限：慢速推理常过度探索所有可能路径，导致效率低下；快速推理则依赖模式匹配而非真正理解逻辑，易遗漏关键信息。为此，我们提出FReM：一种灵活推理机制，根据每个问题的复杂度动态调整推理深度。具体而言，FReM利用合成参考问答样例提供明确的思维链，使简单问题能高效处理，复杂问题则允许深入推理。该机制帮助快速推理模型摆脱表面匹配，同时缩小慢速推理模型的探索空间，避免无谓消耗。在七个问答数据集上的实验表明，FReM显著提升了推理准确率与可扩展性，尤其在复杂多跳问题上表现突出，展示了其推动LCQA方法发展的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。