4 papers
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
Erum Mushtaq, Duygu Nur Yaldiz, Yavuz Faruk Bakman +4
Continual self-supervised learning (CSSL) learns a series of tasks sequentially on the unlabeled data. Two main challenges of continual learning are catastrophic forgetting and tas…
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates +5
Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize…
Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
Tiantian Feng, Dimitrios Dimitriadis, Shrikanth Narayanan
Recent advances in foundation models have enabled audio-generative models that produce high-fidelity sounds associated with music, events, and human actions. Despite the success ac…
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates +3
Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a poten…