# Are EEG-to-Text Models Working?

arXiv: https://arxiv.org/abs/2405.06459 · HTML: https://mlsanity.com/paper/2405.06459/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 8 of 8)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification](https://mlsanity.com/paper/2112.02690/) (2021)
- [ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation](https://mlsanity.com/paper/1912.00903/) (2019)
- [UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language](https://mlsanity.com/paper/2307.05355/) (2023)
- [NeuSpeech: Decode Neural signal as Speech](https://mlsanity.com/paper/2403.01748/) (2024)
- [BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision](https://mlsanity.com/paper/2309.12056/) (2023)

## Built on by (most cited first, 30 of 32)

- [The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning](https://mlsanity.com/paper/2406.04328/) (2024)
- [LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale](https://mlsanity.com/paper/2506.02098/) (2025)
- [MAD: Multi-Alignment MEG-to-Text Decoding](https://mlsanity.com/paper/2406.01512/) (2024)
- [Unlocking Non-Invasive Brain-to-Text](https://mlsanity.com/paper/2505.13446/) (2025)
- [Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals](https://mlsanity.com/paper/2405.11459/) (2024)
- [NeuGPT: Unified multi-modal Neural GPT](https://mlsanity.com/paper/2410.20916/) (2024)
- [MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training](https://mlsanity.com/paper/2602.02494/) (2026)
- [Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation](https://mlsanity.com/paper/2505.17099/) (2025)
- [Towards Linguistic Neural Representation Learning and Sentence Retrieval from Electroencephalogram Recordings](https://mlsanity.com/paper/2408.04679/) (2024)
- [BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation](https://mlsanity.com/paper/2410.14971/) (2024)
- [Pretraining Large Brain Language Model for Active BCI: Silent Speech](https://mlsanity.com/paper/2504.21214/) (2025)
- [Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex](https://mlsanity.com/paper/2505.15813/) (2025)
- [Foundation Models for Cross-Domain EEG Analysis Application: A Survey](https://mlsanity.com/paper/2508.15716/) (2025)
- [A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond](https://mlsanity.com/paper/2502.12048/) (2025)
- [Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset](https://mlsanity.com/paper/2510.21038/) (2025)
- [The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100](https://mlsanity.com/paper/2609.03231/) (2026)
- [The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding](https://mlsanity.com/paper/2609.10296/) (2026)
- [Decoding Linguistic Representations of Human Brain](https://mlsanity.com/paper/2407.20622/) (2024)
- [EEG-to-Text Translation: A Model for Deciphering Human Brain Activity](https://mlsanity.com/paper/2505.13936/) (2025)
- [Bridging Brain with Foundation Models through Self-Supervised Learning](https://mlsanity.com/paper/2506.16009/) (2025)
- [Neurocognitive Modeling for Text Generation: Deep Learning Architecture for EEG Data](https://mlsanity.com/paper/2509.07202/) (2025)
- [DELTA: Language Diffusion-based EEG-to-Text Architecture](https://mlsanity.com/paper/2511.21746/) (2025)
- [Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding](https://mlsanity.com/paper/2603.03312/) (2026)
- [Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding](https://mlsanity.com/paper/2604.08537/) (2026)
- [Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence](https://mlsanity.com/paper/2608.16975/) (2026)
- [Cross-Sensory Brain Passage Retrieval: Scaling Beyond Visual to Audio](https://mlsanity.com/paper/2601.14001/) (2026)
- [MEGnifying Emotion: Sentiment Analysis from Annotated Brain Data](https://mlsanity.com/paper/2601.18792/) (2026)
- [Measuring Robustness of Speech Recognition from MEG Signals Under Distribution Shift](https://mlsanity.com/paper/2604.04129/) (2026)
- [Brain-CLIPLM: Semantic Compression for EEG-to-Text Decoding](https://mlsanity.com/paper/2604.16370/) (2026)
- [MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors](https://mlsanity.com/paper/2605.31173/) (2026)

## Abstract (arXiv)

This work critically analyzes existing models for open-vocabulary EEG-to-Text translation. We identify a crucial limitation: previous studies often employed implicit teacher-forcing during evaluation, artificially inflating performance metrics. Additionally, they lacked a critical benchmark - comparing model performance on pure noise inputs. We propose a methodology to differentiate between models that truly learn from EEG signals and those that simply memorize training data. Our analysis reveals that model performance on noise data can be comparable to that on EEG data. These findings highlight the need for stricter evaluation practices in EEG-to-Text research, emphasizing transparent reporting and rigorous benchmarking with noise inputs. This approach will lead to more reliable assessments of model capabilities and pave the way for robust EEG-to-Text communication systems. Code is available at https://github.com/NeuSpeech/EEG-To-Text