4 papers
Render Before Reading: Visual Rendering as a Prompt Injection Defense
Jie Zhang, Andrei Baroian, Jan N. van Rijn +2
Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by…
Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts
Andrei Baroian, Rutger Berger
Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts…
Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER
Andrei Baroian
We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large),…
Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training
Andrei Baroian, Kasper Notebomer
Transformer-based language models traditionally use uniform (isotropic) layer sizes, yet they ignore the diverse functional roles that different depths can play and their computati…