Analyzing the Effectiveness of Listwise Reranking with Positional Invariance on Temporal Generalizability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoon, Soyoung, Kim, Jongyoon, Hwang, Seung-won
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912051103793152
author Yoon, Soyoung
Kim, Jongyoon
Hwang, Seung-won
author_facet Yoon, Soyoung
Kim, Jongyoon
Hwang, Seung-won
contents This working note outlines our participation in the retrieval task at CLEF 2024. We highlight the considerable gap between studying retrieval performance on static knowledge documents and understanding performance in real-world environments. Therefore, Addressing these discrepancies and measuring the temporal persistence of IR systems is crucial. By investigating the LongEval benchmark, specifically designed for such dynamic environments, our findings demonstrate the effectiveness of a listwise reranking approach, which proficiently handles inaccuracies induced by temporal distribution shifts. Among listwise rerankers, our findings show that ListT5, which effectively mitigates the positional bias problem by adopting the Fusion-in-Decoder architecture, is especially effective, and more so, as temporal drift increases, on the test-long subset.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06716
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analyzing the Effectiveness of Listwise Reranking with Positional Invariance on Temporal Generalizability
Yoon, Soyoung
Kim, Jongyoon
Hwang, Seung-won
Information Retrieval
This working note outlines our participation in the retrieval task at CLEF 2024. We highlight the considerable gap between studying retrieval performance on static knowledge documents and understanding performance in real-world environments. Therefore, Addressing these discrepancies and measuring the temporal persistence of IR systems is crucial. By investigating the LongEval benchmark, specifically designed for such dynamic environments, our findings demonstrate the effectiveness of a listwise reranking approach, which proficiently handles inaccuracies induced by temporal distribution shifts. Among listwise rerankers, our findings show that ListT5, which effectively mitigates the positional bias problem by adopting the Fusion-in-Decoder architecture, is especially effective, and more so, as temporal drift increases, on the test-long subset.
title Analyzing the Effectiveness of Listwise Reranking with Positional Invariance on Temporal Generalizability
topic Information Retrieval
url https://arxiv.org/abs/2407.06716