A RAG pipeline combining EEG semantic embedding, vector retrieval, and LLM refinement outperforms random baseline by 30% in cosine similarity on ZuCo EEG data for sentence decoding without teacher forcing.
The Llama 3 herd of models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RAG-based EEG-to-Text Translation Using Deep Learning and LLMs
A RAG pipeline combining EEG semantic embedding, vector retrieval, and LLM refinement outperforms random baseline by 30% in cosine similarity on ZuCo EEG data for sentence decoding without teacher forcing.