论文标题
语言模型可以执行绑架常识性推理吗？
Can Language Models perform Abductive Commonsense Reasoning?
论文作者
论文摘要
绑架推理是一组观察结果推断最合理的假设的任务。在文献中，社区通过对可能与过去的观察和未来观察不矛盾的假设进行分类/产生可能的假设来解决这一挑战。解决此问题的一些最著名的基准是ANLI和ANLG（发音为Alpha-Nli和Alpha-NLG）。在本报告中，我回顾了一些试图解决这一挑战，重新实现基线模型并分析当前方法所具有的一些弱点的方法。代码和重新实现的结果可在此链接中获得。
Abductive Reasoning is a task of inferring the most plausible hypothesis given a set of observations. In literature, the community has approached to solve this challenge by classifying/generating a likely hypothesis that does not contradict with a past observation and future observation. Some of the most well-known benchmarks that tackle this problem are aNLI and aNLG (pronounced as alpha-NLI and alpha-NLG). In this report, I review over some of the methodologies that were attempted to solve this challenge, re-implement the baseline models, and analyze some of the weaknesses that current approaches have. The code and the re-implemented results are available at this link.
