5 papers
Continual Learning Using a Kernel-Based Method Over Foundation Models
Saleh Momeni, Sahisnu Mazumder, Bing Liu
Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: cat…
In-context Continual Learning Assisted by an External Continual Learner
Saleh Momeni, Sahisnu Mazumder, Zixuan Ke +1
Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has b…
Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
Shachi H Kumar, Saurav Sahay, Sahisnu Mazumder +6
Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are sus…
Lifelong and Continual Learning Dialogue Systems
Sahisnu Mazumder, Bing Liu
Dialogue systems, commonly known as chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with u…
Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning
Alexander Politowicz, Sahisnu Mazumder, Bing Liu
Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enf…