SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning
This addresses the problem of enhancing interpretability and trustworthiness in QA systems for users, though it is incremental as it builds on existing RL methods by incorporating structured relationships.
The paper tackles the challenge of generating structured explanations for question-answering systems by proposing SEER, a reinforcement learning method that uses a structure-based return and fine-grained rewards, resulting in absolute improvements of 6.9% on EntailmentBank and 4.4% on STREET benchmark over state-of-the-art methods.
Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured explanations demand models to perform intricately structured reasoning, which poses great challenges. Most existing methods focus on single-step reasoning through supervised learning, ignoring logical dependencies between steps. Moreover, existing reinforcement learning (RL) based methods overlook the structured relationships, underutilizing the potential of RL 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 different reasoning steps. In addition, we 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. Our code is available at https://github.com/Chen-GX/SEER.