7 papers
BayesPrompt: human readable prompts that make sense
Franky Kevin Nando Tezoh, Ali Hussaini Umar, Alessandro Laio +2
Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity…
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Ludovica de Paolis, Marco Baroni, Alessandro Laio +1
In computational vision science, Convolutional Neural Networks (CNNs) have emerged as a popular model of biological vision because of the alignment they can exhibit with neural and…
Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks
Ali Hussaini Umar, Alessandro Laio
Neural networks are known to develop latent representations that are , namely structurally similar across networks trained with different architectures, training protocols…
Differential syntactic and semantic encoding in LLMs
Santiago Acevedo, Alessandro Laio, Marco Baroni
We study how syntactic and semantic information is encoded in inner layer representations of Large Language Models (LLMs), focusing on the very large DeepSeek-V3. We find that, by…
The Effect of Label Noise on the Information Content of Neural Representations
Ali Hussaini Umar, Franky Kevin Nando Tezoh, Jean Barbier +2
In supervised classification tasks, models are trained to predict a label for each data point. In real-world datasets, these labels are often noisy due to annotation errors. While…
A quantitative analysis of semantic information in deep representations of text and images
Santiago Acevedo, Andrea Mascaretti, Riccardo Rende +3
It was recently observed that the representations of different models that process identical or semantically related inputs tend to align. We analyze this phenomenon using the Info…