7 papers
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
Irina Proskurina, Mayank Kumar, Oyindolapo O. Komolafe
Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question…
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data
Irina Proskurina, Antoine Gourru, Julien Velcin
Generative models trained on artificially generated data have been shown to exhibit model collapse, resulting in significant performance degradation. As synthetic content increasin…
Fair-GPTQ: Bias-Aware Quantization for Large Language Models
Irina Proskurina, Guillaume Metzler, Julien Velcin
The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to lower-precision integers. However…
HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection
Irina Proskurina, Marc-Antoine Carpentier, Julien Velcin
Optimization of offensive content moderation models for different types of hateful messages is typically achieved through continued pre-training or fine-tuning on new hate speech b…
RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts
Darya Kharlamova, Irina Proskurina
Many errors in student essays can be explained by influence from the native language (L1). L1 interference refers to errors influenced by a speaker's first language, such as using…
Histoires Morales: A French Dataset for Assessing Moral Alignment
Thibaud Leteno, Irina Proskurina, Antoine Gourru +4
Aligning language models with human values is crucial, especially as they become more integrated into everyday life. While models are often adapted to user preferences, it is equal…