BERT Rankers are Brittle: a Study using Adversarial Document Perturbations

23 June 2022

Papers citing "BERT Rankers are Brittle: a Study using Adversarial Document Perturbations"

8 / 8 papers shown

Title
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence Mohsen Fayyaz Ali Modarressi Hinrich Schuetze Nanyun Peng 123 3 0 06 Mar 2025
Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective Yu-An Liu Ruqing Zhang Jiafeng Guo Maarten de Rijke Yixing Fan Xueqi Cheng 113 11 0 09 Jul 2024
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models Yuansan Liu Ruqing Zhang Jiafeng Guo Maarten de Rijke Yixing Fan Xueqi Cheng AAML 107 15 0 02 Apr 2024
Towards Effective Paraphrasing for Information Disguise Anmol Agarwal Shrey Gupta Vamshi Krishna Bonagiri Manas Gaur Joseph M. Reagle Ponnurangam Kumaraguru 72 3 0 08 Nov 2023
Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method Yuansan Liu Ruqing Zhang Jiafeng Guo Maarten de Rijke Wei Chen Yixing Fan Xueqi Cheng AAML 77 29 0 19 Aug 2023
Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection Xuanang Chen Xianpei Han Le Sun Yingfei Sun AAML 105 5 0 31 Jul 2023
Towards Imperceptible Document Manipulations against Neural Ranking Models Xuanang Chen Xianpei Han Zheng Ye Le Sun Yingfei Sun AAML 79 17 0 03 May 2023
A Study on FGSM Adversarial Training for Neural Retrieval Simon Lupart Stéphane Clinchant AAML 87 7 0 25 Jan 2023