Papers by Pallavi Gudipati

Copied to clipboard

Challenge:	Existing studies show that retrievers underperform on rarer entities that share a name . open-domain tasks require a knowledge source to perform reasoning and produce an answer .
Approach:	They propose an evaluation benchmark for retrieving entities that share a name . they define Ambiguous Entity Retrieval sets as a collection of entities that have a common name - and query about those entities.
Outcome:	The proposed sets underperform on rarer entities that share a name . the retrievers exhibit popularity bias, and are twice as likely to retrieve erroneous documents .