FSM：一种基于有限状态机的零样本提示范式，用于多跳问答
FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering
AI总结：
本文提出基于有限状态机的零样本提示范式FSM，通过将多跳问答迭代分解为子问题并逐步自我纠正，在Musique等复杂数据集上提升推理准确性并缓解幻觉。
摘要：
采用思维链（COT）提示的大语言模型（LLMs）在简单自然语言推理任务上已展现出令人印象深刻的能力。然而，由于幻觉、错误传播和有限上下文长度等挑战，它们在多跳问答（MHQA）任务上往往表现不佳。我们提出一种提示方法——有限状态机（FSM），以增强LLM在复杂任务上的推理能力，同时提升有效性和可信度。与COT方法不同，FSM通过将问题迭代分解为多轮子问题并及时自我纠正来处理MHQA，从而提高每一步答案的准确性。具体而言，FSM一次处理一个子问题，并以类似自动机的形式根据当前结果和状态决定下一步。在基准上的实验证明了我们方法的有效性。尽管我们的方法在相对简单的数据集上与基线表现相当，但它在Musique等具有挑战性的数据集上表现优异。此外，该方法缓解了幻觉现象，即使中间推理出现错误，也能恢复正确的最终答案。而且，我们的方法提高了LLM遵循指定输出格式要求的能力，显著降低了解读答案的难度和重新格式化的需要。
英文摘要：
Large Language Models (LLMs) with chain-of-thought (COT) prompting have demonstrated impressive abilities on simple nature language inference tasks. However, they tend to perform poorly on Multi-hop Question Answering (MHQA) tasks due to several challenges, including hallucination, error propagation and limited context length. We propose a prompting method, Finite State Machine (FSM) to enhance the reasoning capabilities of LLM for complex tasks in addition to improved effectiveness and trustworthiness. Different from COT methods, FSM addresses MHQA by iteratively decomposing a question into multi-turn sub-questions, and self-correcting in time, improving the accuracy of answers in each step. Specifically, FSM addresses one sub-question at a time and decides on the next step based on its current result and state, in an automaton-like format. Experiments on benchmarks show the effectiveness of our method. Although our method performs on par with the baseline on relatively simpler datasets, it excels on challenging datasets like Musique. Moreover, this approach mitigates the hallucination phenomenon, wherein the correct final answer can be recovered despite errors in intermediate reasoning. Furthermore, our method improves LLMs' ability to follow specified output format requirements, significantly reducing the difficulty of answer interpretation and the need for reformatting.
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。
