Anna Bavaresco

I am currently an ELLIS PhD student at the University of Amsterdam. I am supervised by Raquel Fernández and co-supervised by Marie-Francine Moens (KU Leuven). My research focuses on computational linguistics, vision-and-language interaction, and computational cognitive neuroscience.


News

May 2025

LLMs As Judges Accepted to ACL2025

The revised version of this fruitful collaboration has been accepted to ACL 2025! In this study, we evaluate the reliability of LLMs as judges of machine-generated outputs. If you're curious to know more,have a look at the latest preprint!

LLMs As Judges Accepted to ACL2025

May 2025

LLMs As Judges Accepted to ACL2025

The revised version of this fruitful collaboration has been accepted to ACL 2025! In this study, we evaluate the reliability of LLMs as judges of machine-generated outputs. If you're curious to know more,have a look at the latest preprint!

May 2025

New Paper Accepted to CoNLL

In this paper, we evaluate vision-language and language-only models in their ability to capture experiential aspects of meaning and align with fMRI responses to single words. Check out the pre-print to learn more!

New Paper Accepted to CoNLL

May 2025

New Paper Accepted to CoNLL

In this paper, we evaluate vision-language and language-only models in their ability to capture experiential aspects of meaning and align with fMRI responses to single words. Check out the pre-print to learn more!

Jul 2024

New ArXiv Preprint

In this work, we investigate the alignment between brain fMRI responses to concepts and concept representations extracted from multiple vision-and-language, language-only, and vision-only models. Our results indicate that vision-and-language models might be better suited to capture the multimodal aspects of concept representations. I am very thankful to Marianne for everything I've learnt from her during this project and to Sandro and Raquel for their helpful supervision!

New ArXiv Preprint

Jul 2024

New ArXiv Preprint

In this work, we investigate the alignment between brain fMRI responses to concepts and concept representations extracted from multiple vision-and-language, language-only, and vision-only models. Our results indicate that vision-and-language models might be better suited to capture the multimodal aspects of concept representations. I am very thankful to Marianne for everything I've learnt from her during this project and to Sandro and Raquel for their helpful supervision!

Jun 2024

New ArXiv Preprint

This paper evaluates the reliability of LLMs as judges of machine-generated outputs and was carried out together with an amazing team of researchers. Check out the preprint to discover more about this project.

New ArXiv Preprint

Jun 2024

New ArXiv Preprint

This paper evaluates the reliability of LLMs as judges of machine-generated outputs and was carried out together with an amazing team of researchers. Check out the preprint to discover more about this project.

May 2024

Paper Accepted to ACL Main

This new paper focuses on evaluating the ad understanding abilities of contrastive vision-and-language models. Check out the preprint to find out more. Many thanks to Raquel and Alberto for supervising this project!

Paper Accepted to ACL Main

May 2024

Paper Accepted to ACL Main

This new paper focuses on evaluating the ad understanding abilities of contrastive vision-and-language models. Check out the preprint to find out more. Many thanks to Raquel and Alberto for supervising this project!

Jun 2023

Joined the DMG as PhD Student

Excited to start this new adverture at the ILLC! I'll be joining the dialogue modelling group, led by Raquel Fernández.

Joined the DMG as PhD Student

Jun 2023

Joined the DMG as PhD Student

Excited to start this new adverture at the ILLC! I'll be joining the dialogue modelling group, led by Raquel Fernández.

Jan 2023

Publication on Neural Networks

In this work, we look at how pruning can be used to improve the alignment between DNN embeddings and human similarity judgments. I'm extremely grateful for being part of this project led by Homa Priya Tarigopula and supervised by Uri Hasson!

Publication on Neural Networks

Jan 2023

Publication on Neural Networks

In this work, we look at how pruning can be used to improve the alignment between DNN embeddings and human similarity judgments. I'm extremely grateful for being part of this project led by Homa Priya Tarigopula and supervised by Uri Hasson!

Jan 2023

Joined CIMeC As Research Assistant

Happy to join Uri Hasson's lab at CIMeC as a research assistant after collaborating with them for my internship and master's thesis!

Joined CIMeC As Research Assistant

Jan 2023

Joined CIMeC As Research Assistant

Happy to join Uri Hasson's lab at CIMeC as a research assistant after collaborating with them for my internship and master's thesis!