- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper addresses the problem of signal reliance in EEG-to-text decoding, where pretrained language models may generate text without sufficiently utilizing EEG signals. The authors propose NeuroLens, which combines a bidirectional S4D encoder, reliance-aware training, and decoder prior dampening to improve text generation and encourage greater dependence on EEG signals.
Critical strengths
- The paper addresses an important issue in EEG-to-text decoding and adopts a problem-driven approach, identifying limitations of existing methods and designing specific components to address them
- The paper is well-structured and logically organized, making the motivation, methodology, and experimental results easy to follow.
- The paper adopts a relatively rigorous evaluation protocol, including sentence-disjoint splits, decoding without teacher forcing, and shuffled/zero EEG controls to assess the model's dependence on neural signals.
- NeuroLens improves BLEU-4 from 0.76 to 1.46 over the strongest reported baseline, while shuffled EEG reduces BLEU-4 by 68%, indicating sensitivity to the paired EEG input.
Critical weaknesses
- The paper mainly compares against a limited set of existing baselines, while recent works such as [1] and [2] also investigate EEG-grounded text generation and reliance on language priors. A more comprehensive discussion and, where evaluation protocols permit, quantitative comparisons would help clarify the contribution of NeuroLens.
- The ablation results do not convincingly establish the contributions of individual components. In Table 3, an independent full-model run shows a 21% decrease in BLEU-4, exceeding the reported gains from several proposed modules. Moreover, removing InfoNCE, word dropout, or the attention gate improves performance. These results raise concerns about the stability of the reported improvements and the necessity of certain components.
- Although shuffled-EEG experiments demonstrate input sensitivity, they do not necessarily establish reliance on sentence-specific semantic information. Additional controls, such as length-matched and within-subject EEG shuffling, would strengthen this claim.
- Setting decoder self-attention to zero is too extreme and may limit the decoder's ability to utilize linguistic context.
Reference
[1] Liu, Xiaozhao, Dinggang Shen, and Xihui Liu. "Learning interpretable representations leads to semantically faithful eeg-to-text generation." arXiv preprint arXiv:2505.17099 (2025).
[2] Wang, Yuchen, et al. "Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding." arXiv preprint arXiv:2603.03312 (2026).
Questions for authors
- Could the authors clarify the differences between NeuroLens and recent EEG-to-text methods such as GLIM and SemKey, and explain whether comparisons under a unified evaluation protocol are feasible?
- Could the authors further clarify the effectiveness of individual components, given the substantial BLEU-4 variation between the two full-model runs in Table 3?
- How do the authors account for potential confounding factors, such as sequence length and subject-specific differences, in the shuffled-EEG experiments?
Since there are no response from the authors, I will maintain my original score.