Stable Random Sampling (SRS): A New Method to Refine Causal Masking in Decoder-Only Transformer
In current language modelling, the decoder-only Transformer architecture with causal masking has become a cornerstone, demonstrating exceptional performance across various tasks. However, we have identified two significant limitations: First, causal masking presents a substantial obstacle to further
Authors
- Jiarui Li (ORCID: https://orcid.org/0000-0002-2358-0939)
- Shuhao Zhang (ORCID: https://orcid.org/0000-0002-0301-5983)
- Jiayi Yu (ORCID: https://orcid.org/0000-0002-4204-172X)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.4108/eai.21-11-2024.2354592
- Primary Topic
- Ultrasonics and Acoustic Wave Propagation
- Type
- article
- Field-Weighted Citation Impact
- 0.00