论文标题
我们需要的问题分解单位吗？
Is a Question Decomposition Unit All We Need?
论文作者
论文摘要
大型语言模型（LMS）在许多自然语言处理（NLP）基准测试方面已经取得了最先进的表现。随着新基准的越来越多，我们建立了更大，更复杂的LMS。但是，由于与之相关的成本，时间和环境影响，建造新的LMS可能不是理想的选择。我们探索了一条替代路线：我们可以通过根据模型的优势来表达数据来修改数据，从而使模型更容易回答问题？我们调查人类是否可以将一个棘手的问题分解为一组简单的问题，这些问题相对容易解决。我们分析了涉及各种推理的一系列数据集，并发现确实可以通过分解显着提高模型性能（Roberta-squad以及Roberta-Squad的24％，而29％）通过分解进行分解。我们的方法提供了一种可行的选择，可以使人们以有意义的方式参与NLP研究。我们的发现表明，人类在循环问题分解（HQD）可能会为建造大型LMS提供另一种途径。代码和数据可从https://github.com/pruthvi98/questiondecomposition获得
Large Language Models (LMs) have achieved state-of-the-art performance on many Natural Language Processing (NLP) benchmarks. With the growing number of new benchmarks, we build bigger and more complex LMs. However, building new LMs may not be an ideal option owing to the cost, time and environmental impact associated with it. We explore an alternative route: can we modify data by expressing it in terms of the model's strengths, so that a question becomes easier for models to answer? We investigate if humans can decompose a hard question into a set of simpler questions that are relatively easier for models to solve. We analyze a range of datasets involving various forms of reasoning and find that it is indeed possible to significantly improve model performance (24% for GPT3 and 29% for RoBERTa-SQuAD along with a symbolic calculator) via decomposition. Our approach provides a viable option to involve people in NLP research in a meaningful way. Our findings indicate that Human-in-the-loop Question Decomposition (HQD) can potentially provide an alternate path to building large LMs. Code and data is available at https://github.com/Pruthvi98/QuestionDecomposition
