Prompt learning to mitigate catastrophic forgetting in cross-lingual transfer for open-domain...

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

X Wang, Y Zhang, T Chen, S Gao, S **, X Yang… - arxiv preprint arxiv …, 2023 - arxiv.org
Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving,
following instructions, and ensuring safety. However, the continual learning aspect of these …
Guardar Citar Citado por 9 Artículos relacionados Las 3 versiones Versión en HTML