Bc. Michal Spiegel

2025

• Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering

  ŠTEFÁNIK Michal MICKUS Timothee SPIEGEL Michal KADLČÍK Marek KUCHAŘ Josef

  Článek ve sborníku

  Findings of the Association for Computational Linguistics: EMNLP 2025, rok: 2025

• Negation: A Pink Elephant in the Large Language Models' Room?

  VRABCOVÁ Tereza KADLČÍK Marek SOJKA Petr ŠTEFÁNIK Michal SPIEGEL Michal

  Výzkumná zpráva

  Rok: 2025

• Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers

  KADLČÍK Marek ŠTEFÁNIK Michal MICKUS Timothee SPIEGEL Michal KUCHAŘ Josef

  Článek ve sborníku

  Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, rok: 2025

• Towards the Roots of the Negation Problem: A Multilingual NLI Dataset and Model Scaling Analysis

  VRABCOVÁ Tereza KADLČÍK Marek SOJKA Petr ŠTEFÁNIK Michal SPIEGEL Michal

  Článek ve sborníku

  Findings of the Association for Computational Linguistics: EMNLP 2025, rok: 2025

2024

• IMGTB: A Framework for Machine-Generated Text Detection Benchmarking

  SPIEGEL Michal DOMINIK Macko

  Článek ve sborníku

  Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), rok: 2024

• KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection

  SPIEGEL Michal DOMINIK Macko

  Článek ve sborníku

  Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), rok: 2024