2022
DOI: 10.48550/arxiv.2205.12650
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

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

Abstract: We study unsupervised multi-hop reranking for multi-hop QA (MQA) with open-domain questions. Since MQA requires piecing information from multiple documents, the main challenge thus resides in retrieving and reranking chains of passages that support the reasoning process. Our approach relies on LargE models with Prompt-Utilizing reranking Strategy (LEPUS): we construct an instructionlike prompt based on a candidate document path and compute a relevance score of the path as the probability of generating a given … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 21 publications
0
1
0
Order By: Relevance
“…Concurrent with UPR, PromptRank (Khalifa et al, 2023) is the most related prior work, using demonstrations to re-rank "document paths" for multihop-QA. Details of how they select demonstrations is unclear, motivating us to conduct our own study.…”
Section: Related Workmentioning
confidence: 99%
“…Concurrent with UPR, PromptRank (Khalifa et al, 2023) is the most related prior work, using demonstrations to re-rank "document paths" for multihop-QA. Details of how they select demonstrations is unclear, motivating us to conduct our own study.…”
Section: Related Workmentioning
confidence: 99%