Thiago Soares Laitz

According to our database, Thiago Soares Laitz authored at least 16 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs.

Rodrigo Nogueira, Thales Sales Almeida, Giovana Kerche Bonás, André Roque, Ramon Pires, Hugo Queiroz Abonizio, Thiago Soares Laitz, Celio Larcher, Roseval Malaquias Junior, Marcos Piau

CoRR, May, 2026

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks.

Ramon Pires, Thales Sales Almeida, Celio Larcher Junior, Giovana Kerche Bonás, Hugo Queiroz Abonizio, Marcos Piau, Roseval Malaquias Junior, Thiago Soares Laitz, Rodrigo Nogueira

CoRR, May, 2026

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

Roseval Malaquias Junior, Giovana Kerche Bonás, Thales Sales Almeida, Hugo Queiroz Abonizio, Thiago Soares Laitz, Ramon Pires, Marcos Piau, Celio Larcher, Rodrigo Nogueira

CoRR, May, 2026

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion.

Rodrigo Nogueira, Giovana Kerche Bonás, Thales Sales Almeida, André Roque, Ramon Pires, Hugo Queiroz Abonizio, Thiago Soares Laitz, Celio Larcher, Roseval Malaquias Junior, Marcos Piau

CoRR, April, 2026

MARCA: A Checklist-Based Benchmark for Multilingual Web Search.

Thales Sales Almeida, Giovana Kerche Bonás, Ramon Pires, Celio Larcher, Hugo Queiroz Abonizio, Marcos Piau, Roseval Malaquias Junior, Rodrigo Nogueira, Thiago Soares Laitz

CoRR, April, 2026

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

Giovana Kerche Bonás, Roseval Malaquias Junior, Marcos Piau, Thiago Soares Laitz, Thales Sales Almeida, Hugo Queiroz Abonizio, Celio Larcher, Ramon Pires, Rodrigo Nogueira

CoRR, March, 2026

Sabiá-4 Technical Report.

Thiago Soares Laitz, Thales Sales Almeida, Hugo Queiroz Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás, Marcos Piau, Celio Larcher, Ramon Pires, Rodrigo Nogueira

CoRR, March, 2026

2025

Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation.

Thales Sales Almeida, João Guilherme Alves Santos, Thiago Soares Laitz, Giovana Kerche Bonás

CoRR, September, 2025

2024

Sabiá-3 Technical Report.

Hugo Queiroz Abonizio, Thales Sales Almeida, Thiago Soares Laitz, Roseval Malaquias Junior, Giovana Kerche Bonás, Rodrigo Nogueira, Ramon Pires

CoRR, 2024

ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs.

Fernando Ferraretto, Thiago Soares Laitz, Roberto A. Lotufo, Rodrigo Nogueira

CoRR, 2024

InRanker: Distilled Rankers for Zero-Shot Information Retrieval.

Thiago Soares Laitz, Konstantinos Papakostas, Roberto A. Lotufo, Rodrigo Nogueira

Proceedings of the Intelligent Systems - 34th Brazilian Conference, 2024

SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section.

Leandro Carísio Fernandes, Gustavo Bartz Guedes, Thiago Soares Laitz, Thales Sales Almeida, Rodrigo Nogueira, Roberto A. Lotufo, Jayr Pereira

Proceedings of the Intelligent Systems - 34th Brazilian Conference, 2024

2023

ExaRanker: Explanation-Augmented Neural Ranker.

Fernando Ferraretto, Thiago Soares Laitz, Roberto A. Lotufo, Rodrigo Nogueira

CoRR, 2023

ExaRanker: Synthetic Explanations Improve Neural Rankers.

Fernando Ferraretto, Thiago Soares Laitz, Roberto A. Lotufo, Rodrigo Nogueira

Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023

BLUEX: A Benchmark Based on Brazilian Leading Universities Entrance eXams.

Thales Sales Almeida, Thiago Soares Laitz, Giovana Kerche Bonás, Rodrigo Nogueira

Proceedings of the Intelligent Systems - 12th Brazilian Conference, 2023

2022

NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost.

Thales Sales Almeida, Thiago Soares Laitz, João Seródio, Luiz Henrique Bonifacio, Roberto A. Lotufo, Rodrigo Nogueira

Proceedings of the Third International Conference on Design of Experimental Search & Information REtrieval Systems, 2022