Papers by Ali Veisi
Context-aware Biases for Length Extrapolation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Relative Positional Encoding (RPE) lack the capacity to adapt to different input contexts. |
| Approach: | They propose an additive RPE method that learns token-specific, context-aware biases for each attention head in transformers by dynamically adjusting positional biase based on the input sequence. |
| Outcome: | The proposed method significantly improves the extrapolation performance of existing RPE methods on the fineWeb-Edu-10B and WikiText-103 datasets. |