Tag
This paper investigates how GPT-2 models pre-trained on impossible languages (with disrupted information locality) can recover natural English, showing a bias toward shorter dependency lengths and dissociation between structural and surface recovery.
Researchers propose Brain-CLIPLM, a two-stage EEG-to-text decoding framework using contrastive learning for semantic anchor extraction and a retrieval-grounded LLM with Chain-of-Thought reasoning, achieving 67.55% top-5 sentence retrieval accuracy and suggesting EEG-to-text decoding should focus on recovering compressed semantic content rather than full sentence reconstruction.