activity
20242026
collaborators

8 papers

cs.CY2026

Next-Billion AI Index: The compass for AI utility and adoption in the global majority

Ambrish Rawat, Jessica He, Subhabrata Majumdar +6

Generative AI assessments remain dominated by frontier capability benchmarks that often fail to capture whether systems can be sustainably deployed, adapted, and trusted in locally…

cs.CL2025

Exploring Performance Variations in Finetuned Translators of Ultra-Low Resource Languages: Do Linguistic Differences Matter?

Isabel Gonçalves, Paulo Cavalin, Claudio Pinhanez

Finetuning pre-trained language models with small amounts of data is a commonly-used method to create translators for ultra-low resource languages such as endangered Indigenous lan…

cs.CL2025

CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations

Paulo Cavalin, Cassia Sanctos, Marcelo Grave +2

We introduce \textsc{CAT}, a framework designed to evaluate and visualize the \emph{interplay} of \emph{accuracy} and \emph{response consistency} of Large Language Models (LLMs) un…

cs.CL2025

Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices

Paulo Cavalin, Cassia Sanctos, Marcelo Grave +2

In this work we present the Consistency-Rebalanced Accuracy (CoRA) metric, improving the reliability of Large Language Model (LLM) scores computed on multiple choice (MC) benchmark…

cs.CL2025

A methodological analysis of prompt perturbations and their effect on attack success rates

Tiago Machado, Maysa Malfiza Garcia de Macedo, Rogerio Abreu de Paula +5

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on t…

cs.CL2025

The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks

Claudio Pinhanez, Paulo Cavalin, Cassia Sanctos +2

This work explores the consistency of small LLMs (2B-8B parameters) in answering multiple times the same question. We present a study on known, open-source LLMs responding to 10 re…