- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper asks how much of the gain from lookahead attention gates actually comes from reading a sequence’s own future tokens. The authors retrain each gate from scratch with its lookahead inputs borrowed from a different sequence, which splits the gain into a future-dependent part and a future-free part. In the experiments, the paper finds that in CASTLE, the future-free part dominates early in training but vanishes by 1B tokens. For Selective Attention, most of the benefit also does not need future tokens.
Critical strengths
The presentation of a look ahead gate is novel, as it provides a method to quantify if a model utilizes future lookahead on subsequent tokens.
Critical weaknesses
- Only one model size is mainly explored in the experiments, at 0.16B parameters. This does not even cover the 7B parameter models that are typically used in other training baselines.
- Only perplexity is ever evaluated. Downstream tasks like long-context retrieval or multi-hop reasoning is not explored. Tasks that require lookahead would be especially relevant to evaluate.
- The section 6 ablation is only conducted on one answer point, limiting its generalizability.
- The paper does not provide analysis as to why the pooled gate's future-free part disappears between 0.7B and 1B tokens.
Questions for authors
How would your implementation fare under a long context retrieval task, or multi-document summarization?
How do these future free gates affect larger models like 7B or 13B parameter models?