4 Papers accepted at EACL 2024

(3x Research Track, 1x Findings)

Leonardo Ranaldi, André Freitas, Aligning Large Language Models via Chain-of-Thought Reasoning

Marco Valentino, Danilo S. Carvalho, André Freitas, Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions

Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas, Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement

Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, André Freitas, Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders