← Search

Jean-Stanislas Denain

2 accepted papers

2024

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

ICLR 2024spotlight

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present in the context. We study harmful imitation through the lens…

2021

Grounding Representation Similarity Through Statistical Testing

NeurIPS 2021poster

To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures. Unfortunately, these widely used measures often disagree on fundamenta…

Cited by 99SourcePDFScholar