We describe the setup we used to complete the MultiClinAI-NER task in the SMM4H-HeaRD workshop 2026. In this work we employed a dedicated multilingual encoder model (EuroBERT-610m), two Dutch encoder models trained from scratch on clinical corpora (MedRoBERTa.nl and CardioDeBERTa.nl) and a generic Dutch encoder model (RobBERT2023-large), all finetuned with a 3-layer DNN head. We find that the use of multilingual datasets is potentially beneficial in augmenting the training corpora of monolingual models.

Autoregressive models dominate text generation but suffer from left-to-right decoding constraints that limit efficiency and bidirectional reasoning. Diffusion-based models offer a flexible alternative but face challenges in adapting to discrete text efficiently. We propose LAD (LoRA-Adapted Diffusion), a framework for non-autoregressive generation that adapts LLaMA models for iterative, bidirectional sequence refinement using LoRA adapters. LAD employs a structural denoising objective combining masking with text perturbations (swaps, duplications and span shifts), enabling full sequence editing during generation. We aim to demonstrate that LAD could be a viable and efficient alternative to training diffusion models from scratch, by providing both validation results as well as two interactive demos directly available online:https://ruurdkuiper.github.io/tini-lad/https://huggingface.co/spaces/Ruurd/tini-ladInference and training code:https://github.com/RuurdKuiper/lad-code