4 papers
The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies
Gabriel Garcia
Corruption studies, the standard tool for evaluating chain-of-thought (CoT) faithfulness, infer which steps are ``computationally important'' from accuracy loss when steps are corr…
The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
Gabriel Garcia
Large language models often fail at simple counting tasks, even when items to count are in the prompt. We investigate whether this failure occurs because transformers do not repres…
A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences
Gabriel Lino Garcia, João Renato Ribeiro Manesco, Pedro Henrique Paiola +3
The rapid advancement of large language models (LLMs) has opened new boundaries in the extraction and synthesis of medical knowledge, particularly within evidence synthesis. This p…
Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation
Pedro Henrique Paiola, Gabriel Lino Garcia, João Renato Ribeiro Manesco +3
This study evaluates the performance of large language models (LLMs) as medical agents in Portuguese, aiming to develop a reliable and relevant virtual assistant for healthcare pro…