565 citations · 1.3k across the 33 of their papers we have counts for
36 papers
Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability
Krishnapriya Vishnubhotla, Hillary Dawkins, Isar Nejadgholi +1
Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previous works examined the effects…
From Perceived Effectiveness to Measured Impact: Identity-Aware Evaluation of Automated Counter-Stereotypes
Svetlana Kiritchenko, Anna Kerkhof, Isar Nejadgholi +1
We investigate the effect of automatically generated counter-stereotypes on gender bias held by users of various demographics on social media. Building on recent NLP advancements a…
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Kathleen C. Fraser, Hillary Dawkins, Isar Nejadgholi +1
Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove th…
When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
Hillary Dawkins, Kathleen C. Fraser, Svetlana Kiritchenko
Detecting AI-generated text is a difficult problem to begin with; detecting AI-generated text on social media is made even more difficult due to the short text length and informal,…
Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia
Georgina Curto, Svetlana Kiritchenko, Muhammad Hammad Fahim Siddiqui +2
Eradicating poverty is the first goal in the United Nations Sustainable Development Goals. However, aporophobia -- the societal bias against people living in poverty -- constitutes…
Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse
Rongchen Guo, Isar Nejadgholi, Hillary Dawkins +2
This work provides an explanatory view of how LLMs can apply moral reasoning to both criticize and defend sexist language. We assessed eight large language models, all of which dem…
Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods
Kathleen C. Fraser, Hillary Dawkins, Svetlana Kiritchenko
Large language models (LLMs) have advanced to a point that even humans have difficulty discerning whether a text was generated by another human, or by a computer. However, knowing…
Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals
Phillip Howard, Kathleen C. Fraser, Anahita Bhiwandiwalla +1
With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs…
Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes
Isar Nejadgholi, Kathleen C. Fraser, Anna Kerkhof +1
Gender stereotypes are pervasive beliefs about individuals based on their gender that play a significant role in shaping societal attitudes, behaviours, and even opportunities. Rec…
Uncovering Bias in Large Vision-Language Models with Counterfactuals
Phillip Howard, Anahita Bhiwandiwalla, Kathleen C. Fraser +1
With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs…
Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images
Kathleen C. Fraser, Svetlana Kiritchenko
Following on recent advances in large language models (LLMs) and subsequent chat models, a new wave of large vision-language models (LVLMs) has emerged. Such models can incorporate…
Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers
Isar Nejadgholi, Svetlana Kiritchenko, Kathleen C. Fraser +1
Classifiers tend to learn a false causal relationship between an over-represented concept and a label, which can result in over-reliance on the concept and compromised classificati…
The crime of being poor
Georgina Curto, Svetlana Kiritchenko, Isar Nejadgholi +1
The criminalization of poverty has been widely denounced as a collective bias against the most vulnerable. NGOs and international organizations claim that the poor are blamed for t…
A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?
Kathleen C. Fraser, Svetlana Kiritchenko, Isar Nejadgholi
As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate proper…
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information
Isar Nejadgholi, Esma Balkır, Kathleen C. Fraser +1
Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other im…
Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models
Esma Balkir, Svetlana Kiritchenko, Isar Nejadgholi +1
Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fa…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy
Kathleen C. Fraser, Svetlana Kiritchenko, Esma Balkir
In an effort to guarantee that machine learning model outputs conform with human moral values, recent work has begun exploring the possibility of explicitly training models to lear…
Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection
Esma Balkir, Isar Nejadgholi, Kathleen C. Fraser +1
We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually p…
Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors
Isar Nejadgholi, Kathleen C. Fraser, Svetlana Kiritchenko
Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation. New kinds of…
Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model
Kathleen C. Fraser, Isar Nejadgholi, Svetlana Kiritchenko
Stereotypical language expresses widely-held beliefs about different social categories. Many stereotypes are overtly negative, while others may appear positive on the surface, but…
Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective
Svetlana Kiritchenko, Isar Nejadgholi, Kathleen C. Fraser
The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been d…
Towards Ethics by Design in Online Abusive Content Detection
Svetlana Kiritchenko, Isar Nejadgholi
To support safety and inclusion in online communications, significant efforts in NLP research have been put towards addressing the problem of abusive content detection, commonly de…
On Cross-Dataset Generalization in Automatic Detection of Online Abuse
Isar Nejadgholi, Svetlana Kiritchenko
NLP research has attained high performances in abusive language detection as a supervised classification task. While in research settings, training and test datasets are usually ob…