1.8k citations
- University of ManchesterGB30 papers
- Argonne National LaboratoryUS11 papers
- Fermi National Accelerator LaboratoryUS11 papers
- The University of Texas at ArlingtonUS11 papers
- University of Wisconsin–MadisonUS9 papers
- Science OxfordGB8 papers
- Space Science InstituteUS8 papers
- University College LondonGB8 papers
- Instituto de Física CorpuscularES7 papers
- Iowa State UniversityUS7 papers
- Los Alamos National LaboratoryUS7 papers
- Syracuse UniversityUS7 papers
4 papers · 1 filter
From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling
Mohsinul Kabir, Tasfia Tahsin, Sophia Ananiadou
Current research on bias in language models (LMs) predominantly focuses on data quality, with significantly less attention paid to model architecture and temporal influences of dat…
Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
Mohsinul Kabir, Ajwad Abrar, Sophia Ananiadou
A large number of studies rely on closed-style multiple-choice surveys to evaluate cultural alignment in Large Language Models (LLMs). In this work, we challenge this constrained e…
Disentangled Variational Autoencoder for Emotion Recognition in Conversations
Kailai Yang, Tianlin Zhang, Sophia Ananiadou
In Emotion Recognition in Conversations (ERC), the emotions of target utterances are closely dependent on their context. Therefore, existing works train the model to generate the r…
Cluster-Level Contrastive Learning for Emotion Recognition in Conversations
Kailai Yang, Tianlin Zhang, Hassan Alhuzali +1
A key challenge for Emotion Recognition in Conversations (ERC) is to distinguish semantically similar emotions. Some works utilise Supervised Contrastive Learning (SCL) which uses…