论文标题
通过迭代检索生成推理器的索引解释
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
论文作者
论文摘要
大型语言模型在各种问题答案（QA）基准方面取得了高度性能，但其产出的解释性仍然难以捉摸。最近有人建议结构化解释，称为“综合树”，以解释和检查质量检查系统的答案。为了更好地生成此类需要树，我们提出了一种称为迭代检索生成推理器（IRGR）的架构。我们的模型能够通过系统地从文本前提中产生分步解释来解释给定的假设。 IRGR模型迭代地搜索合适的前提，一次构建一个单一的步骤。与以前的方法相反，我们的方法结合了生成步骤和房屋的检索，允许该模型利用中间结论，并减轻基线编码器解码器模型的输入尺寸限制。我们使用IntailmentBank数据集进行实验，在该数据集中，我们在前提和索引树的生成上都优于现有的基准，总体正确性增长了约300％。
Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
