面向多项选择查询回答的选项感知密集检索
Options-Aware Dense Retrieval for Multiple-Choice query Answering
AI总结：
本文提出 Options Aware Dense Retrieval (OADR) 方法，利用查询-选项嵌入微调检索过程以模拟 oracle 查询嵌入，在 QuALITY 数据集上提升了多项选择问答的证据识别准确率。
摘要：
长上下文多项选择问答任务要求对大量文本源进行稳健推理。由于大多数预训练 transformer 模型被限制为一次仅能处理几百个单词，此类任务的成功完成往往依赖于证据片段（如句子）的识别，这些片段为选择正确答案提供支持证据。鉴于缺乏监督来微调检索过程，该领域的前期研究主要利用预训练密集检索模型。本文提出一种名为 Options Aware Dense Retrieval (OADR) 的新方法来解决这些挑战。ORDA 利用查询-选项嵌入，采用创新方法微调检索，旨在模拟 oracle 查询（即与正确答案配对的查询）的嵌入，以增强对支持证据的识别。通过在 QuALITY 基准数据集上进行的实验，我们证明所提出的模型在性能和准确率上超越了现有基线。
英文摘要：
Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful completion of such tasks often relies on the identification of evidence spans, such as sentences, that provide supporting evidence for selecting the correct answer. Prior research in this domain has predominantly utilized pre-trained dense retrieval models, given the absence of supervision to fine-tune the retrieval process. This paper proposes a novel method called Options Aware Dense Retrieval (OADR) to address these challenges. ORDA uses an innovative approach to fine-tuning retrieval by leveraging query-options embeddings, which aim to mimic the embeddings of the oracle query (i.e., the query paired with the correct answer) for enhanced identification of supporting evidence. Through experiments conducted on the QuALITY benchmark dataset, we demonstrate that our proposed model surpasses existing baselines in terms of performance and accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
