Improving Exposure Allocation in Rankings by Query Generation

Deploying methods that incorporate generated queries in their retrieval process, such as Doc2Query, has been shown to be effective for retrieving the most relevant documents for a user’s query. However, to the best of our knowledge, there has been no work yet on whether generated queries can also be used in the ranking process to achieve other objectives, such as ensuring a fair distribution of exposure in the ranking. Indeed, the amount of exposure that a document is likely to receive depends on the document’s position in the ranking, with lower-ranked documents having a lower probability of being examined by the user. While the utility to users remains the main objective of an Information Retrieval (IR) system, an unfair exposure allocation can lead to lost opportunities and unfair economic impacts for particular societal groups. Therefore, in this work, we conduct a first investigation into whether generating relevant queries can help to fairly distribute the exposure over groups of documents in a ranking. In our work, we build on the effective Doc2Query methods to selectively generate relevant queries for underrepresented groups of documents and use their predicted relevance to the original query in order to re-rank the underexposed documents. Our experiments on the TREC 2022 Fair Ranking Track collection show that using generated queries consistently leads to a fairer allocation of exposure compared to a standard ranking while still maintaining utility.