MuSiQue

AbstractPrompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge is …...

AbstractRecent generative approaches for multi-hop question answering (QA) utilize the fusion-in-decoder method to generate a single sequence output which includes both a final answer and a reasoning path taken to …...