Related papers: If there's a Trigger Warning, then where's the Tri…

We present the first dataset and evaluation results on a newly defined computational task of trigger warning assignment. Labeled corpus data has been compiled from narrative works hosted on Archive of Our Own (AO3), a well-known fanfiction…

Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usually expensive and time-consuming to collect. Thus, a crucial…

Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span -- a word or phrase in the input that evokes the occurrence of an event of interest. Event arguments are then…

Suspense is an important tool in storytelling to keep readers engaged and wanting to read more. However, it has so far not been studied extensively in Computational Literary Studies. In this paper, we focus on one of the elements authors…

Backdoor attacks on text classifiers can cause them to predict a predefined label when a particular "trigger" is present. Prior attacks often rely on triggers that are ungrammatical or otherwise unusual, leading to conspicuous attacks. As a…

Fanfiction, a popular form of creative writing set within established fictional universes, has gained a substantial online following. However, ensuring the well-being and safety of participants has become a critical concern in this…

The prevalence of distressing content on social media raises concerns about users' mental well-being, prompting the use of trigger warnings (TW) and content warnings (CW). However, inconsistent implementation of TW/CW across platforms and…

Effectively identifying threats and mitigating their potential damage during crisis situations, such as natural disasters or violent attacks, is paramount for safeguarding endangered individuals. To tackle these challenges, AI has been used…

The traditional way of sentence-level event detection involves two important subtasks: trigger identification and trigger classifications, where the identified event trigger words are used to classify event types from sentences. However,…

As text generated by large language models proliferates, it becomes vital to understand how humans engage with such text, and whether or not they are able to detect when the text they are reading did not originate with a human writer. Prior…

Propaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at the document level, typically labelling all articles from a propagandistic news outlet as…

Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the…

Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Situations and events evoke emotions in humans, but to what extent do they inform the prediction of emotion detection models? This work investigates how well human-annotated emotion triggers correlate with features that models deemed…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Login notifications intend to inform users about sign-ins and help them protect their accounts from unauthorized access. Notifications are usually sent if a login deviates from previous ones, potentially indicating malicious activity. They…

Online medical forums are a rich and underutilized source of insight into patient concerns, especially regarding medication use. Some of the many questions users pose may signal confusion, misuse, or even the early warning signs of a…