activity
20202024
most citedA Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

22 citations · 53 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL2024★ 1 cited

Revisiting subword tokenization: A case study on affixal negation in large language models

Thinh Hung Truong, Yulia Otmakhova, Karin Verspoor +2

In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative mor…

cs.CL2023★ 1 cited

Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval

Jinrui Yang, Timothy Baldwin, Trevor Cohn

We present Multi-EuP, a new multilingual benchmark dataset, comprising 22K multi-lingual documents collected from the European Parliament, spanning 24 languages. This dataset is de…

cs.CL2023★ 2 cited

Language models are not naysayers: An analysis of language models on negation benchmarks

Thinh Hung Truong, Timothy Baldwin, Karin Verspoor +1

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language model…

cs.CL2023★ 1 cited

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

Xuanli He, Jun Wang, Benjamin Rubinstein +1

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the t…

cs.CL2023★ 1 cited

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

Xuanli He, Qiongkai Xu, Jun Wang +2

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be imp…

cs.CL2023★ 1 cited

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP

Xudong Han, Timothy Baldwin, Trevor Cohn

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions…