SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15838 · ACL · 2024

ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval

Yireun Kim, Jiyeon Kim, Eunbi Choi, Soyoung Yoon, Seung-Won Hwang, Hyeongu Yun

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
soyoung97/ListT5 — 2 of 4
copy not recorded — 1 of 1
FunctionStatusWhere it lives
EncoderWrapper Ran soyoung97/ListT5/train_code/models/FiDT5.py
pointer only (licence: NONE) · get_code("4c281a5a3d35717b")
FiDT5 Ran soyoung97/ListT5/train_code/models/FiDT5.py
pointer only (licence: NONE) · get_code("d5799a134c8250b1")
cross_attention_forward Ran this paper's copy was not recorded; identical code first harvested from andyzoujm/autocast
pointer only · get_code("6bef6bdd6eb44070")
CheckpointWrapper Not yet run soyoung97/ListT5/train_code/models/FiDT5.py
pointer only (licence: NONE) · get_code("f3d610d21ffa004a")
apply_checkpoint_wrapper Not yet run soyoung97/ListT5/train_code/models/FiDT5.py
pointer only (licence: NONE) · get_code("f3acdcf7a36eb548")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose LISTT5, a novel reranking approach based on Fusion-in-Decoder (FiD) that handles multiple candidate passages at both train and inference time. We also introduce an efficient inference framework for listwise ranking based on m-ary tournament sort with output caching. We evaluate and compare our model on the BEIR benchmark for zero-shot retrieval task, demonstrating that LISTT5 (1) outperforms the state-of-the-art RankT5 baseline with a notable +1.3 gain in the average NDCG@10 score, (2) has an efficiency comparable to pointwise ranking models and surpasses the efficiency of previous listwise ranking models, and (3) overcomes the lost-in-the-middle problem of previous listwise rerankers. Our code, model checkpoints, and the evaluation framework are fully open-sourced at https: //github.com/soyoung97/ListT5.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.15838")
get_code_for_paper("2402.15838")
have("2402.15838")

Connect an agent — have() is free.