4 papers
Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering
Michal Štefánik, Timothee Mickus, Marek Kadlčík +2
A majority of recent work in AI assesses models' generalization capabilities through the lens of performance on out-of-distribution (OOD) datasets. Despite their practicality, such…
VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
Josef Kuchař, Marek Kadlčík, Michal Spiegel +1
We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our d…
Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers
Marek Kadlčík, Michal Štefánik, Timothee Mickus +2
Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these…
Attend or Perish: Benchmarking Attention in Algorithmic Reasoning
Michal Spiegel, Michal Štefánik, Marek Kadlčík +1
Can transformers learn to perform algorithmic tasks reliably across previously unseen input/output domains? While pre-trained language models show solid accuracy on benchmarks inco…