Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?
Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa. We argue that one step forward to overcome this limitation is to better understand the behavioral trend of PLMs at each hop over the inference chain. Our critical underlying idea is to mimic human-style reasoning: we envision the multi-hop reasoning process as a sequence of explicit single-hop reasoning steps. To endow PLMs with incremental reasoning skills, we propose a set of inference strategies on relevant facts and distractors allowing us to build automatically generated training datasets. Using the SHINRA and ConceptNet resources jointly, we empirically show the effectiveness of our proposal on multiple-choice question answering and reading comprehension, with a relative improvement in terms of accuracy of 68.4% and 16.0% w.r.t. classic PLMs, respectively.
PDF Abstract
ConceptNet
RACE
