4 papers
Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
Bruno Bianchi, Diego Tiscornia, Matias Travizano +1
Since the advent of Large Language Models (LLMs), a significant area of research has focused on their intrinsic biases, particularly in political discourse. This study investigates…
Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation
Nicolas Martorell, Bruno Bianchi
Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear pro…
Modeling cognitive processes of natural reading with transformer-based Language Models
Bruno Bianchi, FermÃn Travi, Juan E. Kamienkowski
Recent advances in Natural Language Processing (NLP) have led to the development of highly sophisticated language models for text generation. In parallel, neuroscience has increasi…
Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models
Bruno Bianchi, Aakash Agrawal, Stanislas Dehaene +2
Human readers can accurately count how many letters are in a word (e.g., 7 in ``buffalo''), remove a letter from a given position (e.g., ``bufflo'') or add a new one. The human bra…