Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings
Aishik Rakshit, Smriti Singh, Shuvam Keshari +3
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced underst…
cs.CL2023
Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion
Smriti Singh, Cornelia Caragea, Junyi Jessy Li
Situations and events evoke emotions in humans, but to what extent do they inform the prediction of emotion detection models? This work investigates how well human-annotated emotio…