298 citations · 347 across the 14 of their papers we have counts for
14 papers
The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models
Giuseppe Russo, Debora Nozza, Paul Röttger +1
People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral…
A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza +1
Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often…
Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization
Helena Bonaldi, Giuseppe Attanasio, Debora Nozza +1
Recent computational approaches for combating online hate speech involve the automatic generation of counter narratives by adapting Pretrained Transformer-based Language Models (PL…
Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation
Flor Miriam Plaza-del-Arco, Debora Nozza, Dirk Hovy
Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained…
What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns
Anne Lauscher, Debora Nozza, Archie Crowley +2
As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP. Exclusion is particularly harmful in one of the most…
Measuring Harmful Representations in Scandinavian Language Models
Samia Touileb, Debora Nozza
Scandinavian countries are perceived as role-models when it comes to gender equality. With the advent of pre-trained language models and their widespread usage, we investigate to w…
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Federico Bianchi, Pratyusha Kalluri, Esin Durmus +7
Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day.…
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
Paul Röttger, Debora Nozza, Federico Bianchi +1
Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection mod…
The State of Profanity Obfuscation in Natural Language Processing
Debora Nozza, Dirk Hovy
Work on hate speech has made the consideration of rude and harmful examples in scientific publications inevitable. This raises various problems, such as whether or not to obscure p…
Is It Worth the (Environmental) Cost? Limited Evidence for Temporal Adaptation via Continuous Training
Giuseppe Attanasio, Debora Nozza, Federico Bianchi +1
Language is constantly changing and evolving, leaving language models to become quickly outdated. Consequently, we should continuously update our models with new data to expose the…
ferret: a Framework for Benchmarking Explainers on Transformers
Giuseppe Attanasio, Eliana Pastor, Chiara Di Bonaventura +1
As Transformers are increasingly relied upon to solve complex NLP problems, there is an increased need for their decisions to be humanly interpretable. While several explainable AI…
Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
Paul Röttger, Haitham Seelawi, Debora Nozza +2
Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance becau…
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
Giuseppe Attanasio, Debora Nozza, Dirk Hovy +1
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural h…
Language Invariant Properties in Natural Language Processing
Federico Bianchi, Debora Nozza, Dirk Hovy
Meaning is context-dependent, but many properties of language (should) remain the same even if we transform the context. For example, sentiment, entailment, or speaker properties s…