Papers by Paul Swoboda
A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies do not provide insights into the internal mechanisms driving the observed abilities. |
| Approach: | They propose to implement a depth-bounded recurrent mechanism that operates in parallel and stores intermediate results in selected token positions. |
| Outcome: | The proposed model implements a depth-bounded recurrent mechanism that operates in parallel and stores intermediate results in selected token positions. |
PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data (2026.acl-long)
Copied to clipboard
| Challenge: | Existing prompt generation methods are impractical in time and data constrained settings. |
| Approach: | They propose a fast automatic prompt construction algorithm that augments human instructions by generating a small set of few shot examples. |
| Outcome: | The proposed method outperforms existing prompting methods on classification, simplification, and MedQA. |