22 citations · 53 across the 17 of their papers we have counts for
15 papers · 1 filter
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…
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…
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…
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…
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…
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…