Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a
model forgets previously learned information while acquiring new knowledge. As large …

Benefiting from massive corpora and advanced hardware, large language models (LLMs)
exhibit remarkable capabilities in language understanding and generation. However, their …

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the
dynamic world. Existing methods devise the learning module to acquire task-specific …

Machine unlearning can be useful for removing harmful capabilities and memorized text
from large language models (LLMs), but there are not yet standardized methods for …

AI systems sometimes exhibit harmful unintended behaviors post-deployment. This is often
despite extensive diagnostics and debugging by developers. Minimizing risks from models …

Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of
handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit …

Model merging offers an effective strategy to combine the strengths of multiple finetuned
models into a unified model that preserves the specialized capabilities of each. Existing …

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the
dynamic world. Based on parameter-efficient tuning (PET), existing methods devise the …

Large language models (LLMs) can often be made to behave in undesirable ways that they
are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a …

This paper studies the evolving domain of Continual Learning (CL) in large language
models (LLMs), with a focus on developing strategies for efficient and sustainable training …