2 papers
cs.CL2025
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
Dhrupad Bhardwaj, Julia Kempe, Tim G. J. Rudner
To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally ine…
cs.CV2022
ImpressLearn: Continual Learning via Combined Task Impressions
Dhrupad Bhardwaj, Julia Kempe, Artem Vysogorets +2
This work proposes a new method to sequentially train deep neural networks on multiple tasks without suffering catastrophic forgetting, while endowing it with the capability to qui…