A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow users to interactively correct explanation structures through natural language feedback. We introduce MERCURIE - an interactive system that refines its explanations for a given reasoning task by getting human feedback in natural language. Our approach generates graphs that have 40% fewer inconsistencies as compared with the off-the-shelf system. Further, simply appending the corrected explanation structures to the output leads to a gain of 1.2 points on accuracy on defeasible reasoning across all three domains. We release a dataset of over 450k graphs for defeasible reasoning generated by our system at https://tinyurl.com/mercurie .
翻译:我们的目标是让用户通过自然语言反馈来互动纠正解释结构。 我们引入了MERCURIE — 一个互动系统,通过以自然语言获得人类的反馈来完善对特定推理任务的解释。 我们的方法产生的图表比现成系统少40%的不一致之处。 此外, 简单地在输出中附加经更正的解释结构, 导致所有三个域的不可行的推理准确性达到1.2个百分点。 我们发布了一个超过450k 的图表, 用于我们系统在 https://tinyurl.com/mercurie 上产生的不可行的推理。