Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-Field Adaptive Retrieval

About

Document retrieval for tasks such as search and retrieval-augmented generation typically involves datasets that are unstructured: free-form text without explicit internal structure in each document. However, documents can have a structured form, consisting of fields such as an article title, message body, or HTML header. To address this gap, we introduce Multi-Field Adaptive Retrieval (MFAR), a flexible framework that accommodates any number of and any type of document indices on structured data. Our framework consists of two main steps: (1) the decomposition of an existing document into fields, each indexed independently through dense and lexical methods, and (2) learning a model which adaptively predicts the importance of a field by conditioning on the document query, allowing on-the-fly weighting of the most likely field(s). We find that our approach allows for the optimized use of dense versus lexical representations across field types, significantly improves in document ranking over a number of existing retrievers, and achieves state-of-the-art performance for multi-field structured data.

Millicent Li, Tongfei Chen, Benjamin Van Durme, Patrick Xia• 2024

Related benchmarks

TaskDatasetResultRank
Knowledge Graph RetrievalPrime (test)
H@10.409
14
Knowledge Graph RetrievalMAG (test)
H@149
14
Knowledge Graph RetrievalSTaRK PRIME synthetic (test)
Hit@140
13
Knowledge Graph RetrievalSTaRK AMAZON synthetic (test)
Hit@10.53
13
Knowledge Graph RetrievalSTaRK MAG synthetic (test)
Hit@155.9
13
Knowledge Graph RetrievalAmazon (test)
Hit@141.2
12
Showing 6 of 6 rows

Other info

Follow for update