paper-with-me

Papers

Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams

2023-03-29 · Desnes Nunes, Ricardo Primi, Ramon Pires, Roberto Lotufo, Rodrigo Nogueira

The present study aims to explore the capabilities of Language Models (LMs) in tackling high-stakes multiple-choice tests, represented here by the Exame Nacional do Ensino M\'edio (ENEM), a multidisciplinary entrance examination widely adopted by Brazilian universities. This exam poses challenging tasks for LMs, since its questions may span into multiple fields of knowledge, requiring understanding of information from diverse domains. For instance, a question may require comprehension of both statistics and biology to be solved. This work analyzed responses generated by GPT-3.5 and GPT-4 models for questions presented in the 2009-2017 exams, as well as for questions of the 2022 exam, which were made public after the training of the models was completed. Furthermore, different prompt strategies were tested, including the use of Chain-of-Thought (CoT) prompts to generate explanations for answers. On the 2022 edition, the best-performing model, GPT-4 with CoT, achieved an accuracy of 87%, largely surpassing GPT-3.5 by 11 points. The code and data used on experiments are available at https://github.com/piresramon/gpt-4-enem.

📄 PDF Abstract BibTeX arXiv:2303.17003

Code (1)

piresramon/gpt-4-enem 공식 구현

Tasks

Multiple-choice

Methods 이 논문이 사용한 방법론

{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams

2023-11-23 · Ramon Pires, Thales Sales Almeida, Hugo Abonizio, Rodrigo Nogueira

Recent advancements in language models have showcased human-comparable performance in academic entrance exams. However, existing studies often overlook questions that require the integration of visual comprehension, thus…

Alvorada-Bench: Can Language Models Solve Brazilian University Entrance Exams?

2025-08-19 · Henrique Godoy arxiv

Language models are increasingly used in Brazil, but most evaluation remains English-centric. This paper presents Alvorada-Bench, a 4,515-question, text-only benchmark drawn from five Brazilian university entrance examin…

The Direct and Spillover Effects of Large-scale Affirmative Action at an Elite Brazilian University

2023-05-04 · Cecilia Machado, Germán Reyes, Evan Riehl

We examine the effects of an affirmative action policy at an elite Brazilian university that reserved 45 percent of admission slots for Black and low-income students. We find that marginally-admitted students who enrolle…

BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams

2026-06-21 · João Guilherme Alves Santos, Giovana Kerche Bonás, Thiago Laitz, Thales Sales Almeida 외 arxiv

Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended, discursive tasks that demand deeper reasoning and generation capabilitie…

Mathematical Reasoning

Evaluating the Performance of Large Language Models for Spanish Language in Undergraduate Admissions Exams

2023-12-28 · Sabino Miranda, Obdulia Pichardo-Lagunas, Bella Martínez-Seis, Pierre Baldi

This study evaluates the performance of large language models, specifically GPT-3.5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico. Th…