This paper critically evaluates existing EEG-to-Text models, focusing on their performance and the impact of teacher-forcing during evaluation. The authors identify a significant limitation in previous studies: the use of implicit teacher-forcing, which artificially inflates performance metrics. They also note the absence of a critical benchmark comparing model performance on pure noise inputs. To address these issues, the authors propose a methodology to differentiate between models that truly learn from EEG signals and those that merely memorize training data. Their analysis reveals that model performance on noise data can be comparable to that on EEG data, suggesting that current models may not effectively learn from EEG inputs. The findings emphasize the need for stricter evaluation practices, including transparent reporting and rigorous benchmarking with noise inputs, to ensure more reliable assessments of model capabilities. This approach aims to advance the development of robust EEG-to-Text communication systems.This paper critically evaluates existing EEG-to-Text models, focusing on their performance and the impact of teacher-forcing during evaluation. The authors identify a significant limitation in previous studies: the use of implicit teacher-forcing, which artificially inflates performance metrics. They also note the absence of a critical benchmark comparing model performance on pure noise inputs. To address these issues, the authors propose a methodology to differentiate between models that truly learn from EEG signals and those that merely memorize training data. Their analysis reveals that model performance on noise data can be comparable to that on EEG data, suggesting that current models may not effectively learn from EEG inputs. The findings emphasize the need for stricter evaluation practices, including transparent reporting and rigorous benchmarking with noise inputs, to ensure more reliable assessments of model capabilities. This approach aims to advance the development of robust EEG-to-Text communication systems.