2 papers
cs.CL2023
All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation
Pragyan Banerjee, Abhinav Java, Surgan Jandial +4
Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks. Re…
cs.IR2023
HyHTM: Hyperbolic Geometry based Hierarchical Topic Models
Simra Shahid, Tanay Anand, Nikitha Srikanth +3
Hierarchical Topic Models (HTMs) are useful for discovering topic hierarchies in a collection of documents. However, traditional HTMs often produce hierarchies where lowerlevel top…