Search Results for author:
Found 18 papers, 3 papers with code
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies.
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs, including in the context of potentially criminal activities.
Challenges and Applications of Large Language Models
Due to the fast pace of the field, it is difficult to identify the remaining challenges and already fruitful application areas.
Susceptibility to Influence of Large Language Models
Data was collected from 1000 human participants using an online experiment, and 1000 simulated participants using engineered prompts and LLM completion.
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
In this paper, we explore the use of TracIn to improve model performance in the parameter-efficient tuning (PET) setting.
Towards Agile Text Classifiers for Everyone
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots.
Identifying Human Strategies for Generating Word-Level Adversarial Examples
Adversarial examples in NLP are receiving increasing research attention.
Textwash -- automated open-source text anonymisation
The increased use of text data in social science research has benefited from easy-to-access data (e. g., Twitter).
Scene Graph Generation for Better Image Captioning?
We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generated visual relationships to describe images in natural language.
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e. g., the preservation of semantics and grammaticality).
A repeated-measures study on emotional responses after a year in the pandemic
The introduction of COVID-19 lockdown measures and an outlook on return to normality are demanding societal changes.
No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization
For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws.
The Grievance Dictionary: Understanding Threatening Language Use
This paper introduces the Grievance Dictionary, a psycholinguistic dictionary which can be used to automatically understand language use in the context of grievance-fuelled violence threat assessment.
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood.
Measuring Emotions in the COVID-19 Real World Worry Dataset
This resulted in the Real World Worry Dataset of 5, 000 texts (2, 500 short + 2, 500 long texts).
Online influence, offline violence: Language Use on YouTube surrounding the 'Unite the Right' rally
We also observe structural breakpoints in the use of bigrams at the time of the rally, suggesting there are changes in language use within the two groups as a result of the rally.
Uphill from here: Sentiment patterns in videos from left- and right-wing YouTube news channels
We found that the use of two sentiment patterns differed significantly depending on political leaning.
Identifying the sentiment styles of YouTube's vloggers
Vlogs provide a rich public source of data in a novel setting.
