SG-FSM：一种基于有限状态机的自引导零样本提示范式，用于多跳问答
SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
AI总结：
针对多跳问答中幻觉和错误传播问题，提出基于有限状态机的自引导零样本提示范式SG-FSM，通过迭代分解子问题并自我修正，在Musique等数据集上超越强基线。
摘要：
具有思维链提示的大型语言模型（如OpenAI-o1）在自然语言推理任务中展现出了令人印象深刻的能力。然而，由于幻觉、错误传播和上下文长度有限等问题，多跳问答（MHQA）对许多现有模型而言仍然具有挑战性。为了解决这些挑战并增强大型语言模型在多跳问答上的性能，我们提出了自引导提示有限状态机（SG-FSM），旨在增强多跳推理能力。与传统的思维链方法不同，SG-FSM通过迭代地将复杂问题分解为子问题来处理多跳问答，并通过自我修正来提高准确性。它一次处理一个子问题，根据当前上下文和结果动态决定下一步，其运作方式类似于自动机。跨多个基准的实验证明了我们方法的有效性，在诸如Musique等具有挑战性的数据集上超越了强基线。SG-FSM减少了幻觉，使得即使在中间步骤出现错误的情况下也能恢复出正确的最终答案。它还提高了对指定输出格式的遵循度，显著简化了评估过程。
英文摘要：
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.
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。
