Related papers: Mitigating Catastrophic Forgetting in Language Tra…

Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning…

Although multimodal large language models (MLLMs) have achieved impressive performance, the multimodal instruction tuning stage often causes catastrophic forgetting of the base LLM's language ability, even in strong models like Llama3. To…

Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight…

The growing interest in Large Language Models (LLMs) for specialized applications has revealed a significant challenge: when tailored to specific domains, LLMs tend to experience catastrophic forgetting, compromising their general…

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions.…

Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the…

Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

We present ALLaM: Arabic Large Language Model, a series of large language models to support the ecosystem of Arabic Language Technologies (ALT). ALLaM is carefully trained considering the values of language alignment and knowledge transfer…

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains…

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

The advent of large language models (LLMs) has predominantly catered to high-resource languages, leaving a disparity in performance for low-resource languages. Conventional Continual Training (CT) approaches to bridge this gap often…

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage broad generalization. However, it remains unclear how…