collaborators

5 papers

cs.LG2024

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…

cs.CL2024

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…

cs.CL2024

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…

cs.CL2024

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…

cs.LG2024

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…