Elucidating the reasoning process with structured explanations from question
to answer is fundamentally crucial, as it significantly enhances the
interpretability and trustworthiness of question-answering (QA) systems.
However, structured explanations demand models to perform intricate structured
reasoning, which poses great challenges. Most existing methods focus on
single-step reasoning through supervised learning, ignoring logical
dependencies between steps. Meanwhile, existing reinforcement learning
(RL)-based methods overlook the structured relationships, impeding RL's
potential in structured reasoning. In this paper, we propose SEER, a novel
method that maximizes a structure-based return to facilitate structured
reasoning and explanation. Our proposed structure-based return precisely
describes the hierarchical and branching structure inherent in structured
reasoning, effectively capturing the intricate relationships between states. We
also introduce a fine-grained reward function to meticulously delineate diverse
reasoning steps. Extensive experiments show that SEER significantly outperforms
state-of-the-art methods, achieving an absolute improvement of 6.9% over
RL-based methods on EntailmentBank, a 4.4% average improvement on STREET
benchmark, and exhibiting outstanding efficiency and cross-dataset
generalization performance.

通过提出 SEER 方法，我们在建立问答系统中，给出结构化解释，提高系统的可解释性和可靠性；实验证明，SEER 方法显著优于现有方法，在 EntailmentBank 上的绝对改进率达到了 6.9%，在 STREET 基准上平均提升了 4.4%，同时展现出卓越的效率和跨数据集的泛化性能。

SEER: 通过强化学习促进结构化推理和解释

SEER: Facilitating Structured Reasoning and Explanation via  Reinforcement Learning

In this position paper, we propose a way of exploiting formal proofs to put
forward several explainable natural language inference (NLI) tasks. The formal
proofs will be produced by a reliable and high-performing logic-based NLI
system. Taking advantage of the in-depth information available in the generated
formal proofs, we show how it can be used to define NLI tasks with structured
explanations. The proposed tasks can be ordered according to difficulty defined
in terms of the granularity of explanations. We argue that the tasks will
suffer with substantially fewer shortcomings than the existing explainable NLI
tasks (or datasets).

我们提出利用形式证明来推进几个可解释的自然语言推理（NLI）任务的方法，并利用可靠和高性能的基于逻辑的 NLI 系统生成形式证明。通过利用生成的形式证明中的深度信息，我们展示了如何使用它来定义具有结构化解释的 NLI 任务。所提出的任务可以根据解释的粒度难度进行排序，并且我们认为这些任务在许多方面都比现有的可解释 NLI 任务（或数据集）具有更少缺陷。