Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed the desired reasoning to reach the correct answer. Most existing multi-hop QA methods fail to answer a large fraction of sub-questions, even if their parent questions are answered correctly. In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting. Specifically, we first train a model on existing single-hop QA tasks, and then freeze this model and expand it by allocating additional sub-networks for the multi-hop QA task. Moreover, to condition pre-trained language models to stimulate the kind of reasoning required for specific multi-hop questions, we learn soft prompts for the novel sub-networks to perform type-specific reasoning. Experimental results on the HotpotQA benchmark show that PCL is competitive for multi-hop QA and retains good performance on the corresponding single-hop sub-questions, demonstrating the efficacy of PCL in mitigating knowledge loss by forgetting.

翻译：多跳问题解答( QA) 要求对多个文件进行推理, 以解答复杂问题并提供可解释的辅助证据。 但是, 提供辅助性证据不足以证明一个模型已经满足了正确答案的预期推理。 多数现有的多跳QA方法无法解答大部分子问题, 即使他们的父答正确。 在本文中, 我们提议多跳QA快速保存学习框架, 用于多跳QA, 它从多跳QA任务中获取新知识, 同时保存在单跳QA任务中学到的旧知识, 减轻遗忘。 具体地说, 我们首先在现有的单跳QA任务中培训一个模型, 然后冻结这个模型, 并通过分配更多子网络来解答多跳QA任务。 此外, 我们为多跳QA问题设定了预先培训的语言模型, 以刺激所需的推理, 我们学习了新小网络执行特定类型推理的软性提示。 HotpoQA基准的实验结果显示, PCL 具有竞争力, 以多跳式QA 来展示降低 PCMR 的次损。