Few-shot Reranking for Multi-hop QA via Language Model Prompting

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang


Abstract
We study few-shot reranking for multi-hop QA (MQA) 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 language model 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.
Anthology ID:
2023.acl-long.885
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15882–15897
Language:
URL:
https://aclanthology.org/2023.acl-long.885
DOI:
10.18653/v1/2023.acl-long.885
Bibkey:
Cite (ACL):
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, and Lu Wang. 2023. Few-shot Reranking for Multi-hop QA via Language Model Prompting. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15882–15897, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Few-shot Reranking for Multi-hop QA via Language Model Prompting (Khalifa et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.885.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.885.mp4