Thales Sales Almeida

Orcid: 0009-0006-9568-9331

According to our database1, Thales Sales Almeida authored at least 26 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs.
CoRR, May, 2026

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks.
CoRR, May, 2026

Prosa: Rubric-Based Evaluation of LLMs on Real User Chats in Brazilian Portuguese.
CoRR, May, 2026

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion.
CoRR, April, 2026

MARCA: A Checklist-Based Benchmark for Multilingual Web Search.
CoRR, April, 2026

Synthetic Rewriting as a Quality Multiplier: Evidence from Portuguese Continued Pretraining.
CoRR, March, 2026

CAPITU: A Benchmark for Evaluating Instruction-Following in Brazilian Portuguese with Literary Context.
CoRR, March, 2026

Sabiá-4 Technical Report.
CoRR, March, 2026

2025
Curió-Edu 7B: Examining Data Selection Impacts in LLM Continued Pretraining.
CoRR, December, 2025

Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation.
CoRR, September, 2025

BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning.
CoRR, August, 2025

Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime.
CoRR, August, 2025

TiEBe: A Benchmark for Assessing the Current Knowledge of Large Language Models.
CoRR, January, 2025

The interplay between domain specialization and model size: a case study in the legal domain.
CoRR, January, 2025

Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora.
J. Braz. Comput. Soc., 2025

BRoverbs - Measuring how much LLMs understand Portuguese proverbs.
J. Braz. Comput. Soc., 2025

PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese.
IEEE Access, 2025

2024
Sabiá-3 Technical Report.
CoRR, 2024

Sabiá-2: A New Generation of Portuguese Large Language Models.
CoRR, 2024

Measuring Cross-lingual Transfer in Bytes.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section.
Proceedings of the Intelligent Systems - 34th Brazilian Conference, 2024

2023
Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams.
CoRR, 2023

Sabiá: Portuguese Large Language Models.
CoRR, 2023

🐦 Sabiá: Portuguese Large Language Models.
Proceedings of the Intelligent Systems - 12th Brazilian Conference, 2023

BLUEX: A Benchmark Based on Brazilian Leading Universities Entrance eXams.
Proceedings of the Intelligent Systems - 12th Brazilian Conference, 2023

2022
NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost.
Proceedings of the Third International Conference on Design of Experimental Search & Information REtrieval Systems, 2022


  Loading...