2026
Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs
ICLR 2026poster
Large language models (LLMs) adapted to specific languages through continual pretraining or instruction tuning often suffer from catastrophic forgetting, which can lead to factual inaccuracies. This issue is particularly pronounced in multilingual settings, where adaptation may override general worl…