STOC-TOT：面向多跳问答中复杂推理的带约束解码随机思维树
STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering
AI总结：
本文提出STOC-TOT随机思维树推理提示方法，通过将多跳问答问题分解为子问题构建树状推理路径并进行概率估计，结合约束解码减少幻觉，在多个数据集和大语言模型上显著优于现有推理提示。
摘要：
多跳问答（MHQA）要求模型从多个段落中检索并整合信息，以回答复杂问题。近期系统利用大语言模型的能力，将证据检索与推理提示（例如思维链推理）相结合来处理MHQA任务。然而，问题类型（桥接问题与比较问题）和推理类型（顺序推理与并行推理）的复杂性，要求在零样本设置下采用更新颖、更细粒度的提示方法来提升MHQA性能。本文提出STOC-TOT，一种面向MHQA的带约束解码的随机思维树推理提示方法，并在不同问题类型和推理类型上与其他推理提示进行了详细比较。具体而言，我们通过提示模型将原始问题分解为更小的子问题，以形成不同推理路径，从而构建树状推理结构。此外，我们提示模型在每个推理步骤为每条推理路径提供概率估计。在生成答案时，我们对模型执行约束解码，以生成更具依据的答案并减少幻觉。在两个MHQA数据集和五个大语言模型上比较STOC-TOT的实验表明，我们的框架以显著优势优于其他推理提示。
英文摘要：
Multi-hop question answering (MHQA) requires a model to retrieve and integrate information from multiple passages to answer a complex question. Recent systems leverage the power of large language models and integrate evidence retrieval with reasoning prompts (e.g., chain-of-thought reasoning) for the MHQA task. However, the complexities in the question types (bridge v.s. comparison questions) and the reasoning types (sequential v.s. parallel reasonings) require more novel and fine-grained prompting methods to enhance the performance of MHQA under the zero-shot setting. In this paper, we propose STOC-TOT, a stochastic tree-of-thought reasoning prompting method with constrained decoding for MHQA and conduct a detailed comparison with other reasoning prompts on different question types and reasoning types. Specifically, we construct a tree-like reasoning structure by prompting the model to break down the original question into smaller sub-questions to form different reasoning paths. In addition, we prompt the model to provide a probability estimation for each reasoning path at each reasoning step. At answer time, we conduct constrained decoding on the model to generate more grounded answers and reduce hallucination. Experiments comparing STOC-TOT with two MHQA datasets and five large language models showed that our framework outperforms other reasoning prompts by a significant margin.
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。
