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

July 09, 2024 Β· Declared Dead Β· πŸ› Conference and Labs of the Evaluation Forum

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Soyoung Yoon, Jongyoon Kim, Seung-won Hwang arXiv ID 2407.06716 Category cs.IR: Information Retrieval Citations 2 Venue Conference and Labs of the Evaluation Forum Last Checked 4 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted