publications

2026

1. Singular Vectors of Attention Heads Align with Features

   Gabriel Franco, Carson Loughridge, and Mark Crovella

   arXiv preprint arXiv:2602.13524, 2026
2. Finding Highly Interpretable Prompt-Specific Circuits in Language Models

   Gabriel Franco, Lucas M Tassis, Azalea Rohr, and 1 more author

   arXiv preprint arXiv:2602.13483, 2026

2025

1. Disentangling Text and Math in Word Problems: Evidence for the Bidimensional Structure of Large Language Models’ Reasoning

   Pedro Calais, Gabriel Franco, Zilu Tang, and 4 more authors

   In Findings of the Association for Computational Linguistics: ACL 2025, Jul 2025

   Abs DOI

   Do LLMs process text and mathematics as a unified skill, or do these components rely on distinct underlying mechanisms? We investigate this question by disentangling the textual interpretation and mathematical solving steps in word problems drawn from Brazil’s largest college entrance exam (ENEM) and GSM8K, a popular grade school-level benchmark. Using the symbolic solver SymPy, we transform word problems into equivalent purely mathematical representations, isolating equation formulation from textual comprehension. Our extended benchmarks enable a structured analysis of LLM performance across these two dimensions. Through empirical evaluations, we find that small-scale LLMs struggle significantly more with text interpretation than with equation solving, with accuracy dropping by a factor of 2 to 7 when solving full word problems compared to their math-only counterparts. Exploratory factor analysis confirms a bidimensional structure in LLM reasoning, where models exhibit distinct proficiencies in textual and mathematical components, underscoring the need for targeted improvements in language comprehension. By analyzing the latent factors associated with each model, our findings provide a framework for researchers and practitioners to make informed choices when selecting models based on computational costs and the nature of their tasks.

2. MEMSCOPE: Open-Source Kernel-Level Framework for Heterogeneous Memory Characterization

   Golsana Ghaemi, Gabriel Franco, Kazem Taram, and 1 more author

   In 2025 IEEE Real-Time Systems Symposium (RTSS), Jul 2025

   DOI
3. Pinpointing Attention-Causal Communication in Language Models

   Gabriel Franco and Mark Crovella

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, Jul 2025

2024

1. Sparse Attention Decomposition Applied to Circuit Tracing

   Gabriel Franco and Mark Crovella

   arXiv preprint arXiv:2410.00340, Jul 2024

2023

1. Dependence and Model Selection in LLP: The Problem of Variants

   Gabriel Franco, Mark Crovella, and Giovanni Comarela

   In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, CA, USA, Jul 2023

   Abs DOI

   The problem of Learning from Label Proportions (LLP) has received considerable research attention and has numerous practical applications. In LLP, a hypothesis assigning labels to items is learned using knowledge of only the proportion of labels found in predefined groups, called bags. While a number of algorithmic approaches to learning in this context have been proposed, very little work has addressed the model selection problem for LLP. Nonetheless, it is not obvious how to extend straightforward model selection approaches to LLP, in part because of the lack of item labels. More fundamentally, we argue that a careful approach to model selection for LLP requires consideration of the dependence structure that exists between bags, items, and labels. In this paper we formalize this structure and show how it affects model selection. We show how this leads to improved methods of model selection that we demonstrate outperform the state of the art over a wide range of datasets and LLP algorithms.

2. Evaluating LLP Methods: Challenges and Approaches

   Gabriel Franco, Giovanni Comarela, and Mark Crovella

   arXiv preprint arXiv:2310.19065, Jul 2023

2019

1. Towards an Interpretable Metric for DOTA 2 Players: An Unsupervised Learning Approach

   Gabriel Franco, Marcos Henrique Fonseca Ribeiro, and Giovanni Comarela

   In 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), Jul 2019

   DOI

2016

1. Plasmodium Falciparum Infection: In Silico Preliminary Studies

   Andréia Patricia Gomes, Brenda Silveira Valles Moreira, Felipe José Dutra Dias, and 8 more authors

   Abakós, Jul 2016