论文标题
通过语言模型提示，多跳质量质量质量质量质量质量质量质量质量量
Few-shot Reranking for Multi-hop QA via Language Model Prompting
论文作者
论文摘要
我们研究了一些带有开放域问题的多跳质量质量质量质量质量检查的重读。为了减轻需要大量标记的提问对培训的标签对培训的必要性，我们提出了Propptrank，该提示依赖于大型语言模型，这些模型促使多跳路PATH RERARKING。 PROMPTRANK首先构建一个基于指令的提示，该提示包括候选文档路径，然后根据语言模型根据路径提示的问题的条件可能性计算给定问题之间的相关性分数。与在成千上万个示例中训练的最新方法相比，Promptrank在HotPotQA上只有128个训练示例，在HotPotQA上产生了强劲的检索性能-73.6 Rouse@10 by Promptrank vs. 77.8由Pathretriever和77.5，由Multi-Hop Meatensence检索。代码可在https://github.com/mukhal/promptrank上找到
We study few-shot reranking for multi-hop QA with open-domain questions. To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking. PromptRank first constructs an instruction-based prompt that includes a candidate document path and then computes the relevance score between a given question and the path based on the conditional likelihood of the question given the path prompt according to a language model. PromptRank yields strong retrieval performance on HotpotQA with only 128 training examples compared to state-of-the-art methods trained on thousands of examples -- 73.6 recall@10 by PromptRank vs. 77.8 by PathRetriever and 77.5 by multi-hop dense retrieval. Code available at https://github.com/mukhal/PromptRank
