用有限状态机让大模型自动拆解复杂问题，减少错误传播。
SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
- 通过迭代拆解问题并动态决策，实现自我修正的多跳推理
- 在Musique等数据集上超越强基线，中间出错仍能恢复正确答案
- 适合需要高可靠性推理的问答系统，尤其抗幻觉场景
基于链式思维提示的大语言模型（如OpenAI-o1）在自然语言推理任务中表现优异，但在多跳问答（MHQA）任务中仍面临幻觉、错误传播和上下文长度受限等问题。为提升大模型在MHQA中的表现，我们提出自引导有限状态机（SG-FSM），通过迭代分解复杂问题为子问题，并根据当前上下文与结果动态决定下一步，实现自我修正。该方法每次处理一个子问题，行为类似自动机。实验表明，该方法在多个基准测试中有效，优于强基线，在Musique等挑战性数据集上表现突出。SG-FSM显著降低幻觉率，即使出现中间错误也能恢复正确最终答案，同时提高输出格式一致性，大幅简化评估流程。
原文摘要 · Abstract (English)
Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. However, Multi-hop Question Answering (MHQA) remains challenging for many existing models due to issues like hallucination, error propagation, and limited context length. To address these challenges and enhance LLMs' performance on MHQA, we propose the Self-Guiding prompting Finite State Machine (SG-FSM), designed to strengthen multi-hop reasoning abilities. Unlike traditional chain-of-thought methods, SG-FSM tackles MHQA by iteratively breaking down complex questions into sub-questions, correcting itself to improve accuracy. It processes one sub-question at a time, dynamically deciding the next step based on the current context and results, functioning much like an automaton. Experiments across various benchmarks demonstrate the effectiveness of our approach, outperforming strong baselines on challenging datasets such as Musique. SG-FSM reduces hallucination, enabling recovery of the correct final answer despite intermediate errors. It also improves adherence to specified output formats, simplifying evaluation significantly.
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。