4 papers · 1 filter
The Deleuzian Representation Hypothesis
Clément Cornet, Romaric Besançon, Hervé Le Borgne
We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is t…
ManufactuBERT: Efficient Continual Pretraining for Manufacturing
Robin Armingaud, Romaric Besançon
While large general-purpose Transformer-based encoders excel at general language understanding, their performance diminishes in specialized domains like manufacturing due to a lack…
GLiDRE: Generalist Lightweight model for Document-level Relation Extraction
Robin Armingaud, Romaric Besançon
Relation Extraction (RE) is a fundamental task in Natural Language Processing, and its document-level variant poses significant challenges, due to complex interactions between enti…
Explaining How Visual, Textual and Multimodal Encoders Share Concepts
Clément Cornet, Romaric Besançon, Hervé Le Borgne
Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different mode…