Spremljaj
Max Glockner
Max Glockner
Doctoral Researcher, UKP Lab, Technische Universität Darmstadt
Preverjeni e-poštni naslov na ukp.informatik.tu-darmstadt.de
Naslov
Navedeno
Navedeno
Leto
Breaking NLI systems with sentences that require simple lexical inferences
M Glockner, V Shwartz, Y Goldberg
arXiv preprint arXiv:1805.02266, 2018
4432018
Adapterdrop: On the efficiency of adapters in transformers
A Rücklé, G Geigle, M Glockner, T Beck, J Pfeiffer, N Reimers, I Gurevych
arXiv preprint arXiv:2010.11918, 2020
2512020
Missing counter-evidence renders NLP fact-checking unrealistic for misinformation
M Glockner, Y Hou, I Gurevych
arXiv preprint arXiv:2210.13865, 2022
402022
Why do you think that? exploring faithful sentence-level rationales without supervision
M Glockner, I Habernal, I Gurevych
arXiv preprint arXiv:2010.03384, 2020
322020
AmbiFC: Fact-Checking Ambiguous Claims with Evidence
M Glockner, I Staliūnaitė, J Thorne, G Vallejo, A Vlachos, I Gurevych
Transactions of the Association for Computational Linguistics 12, 1-18, 2024
31*2024
Missci: Reconstructing fallacies in misrepresented science
M Glockner, Y Hou, P Nakov, I Gurevych
arXiv preprint arXiv:2406.03181, 2024
82024
Grounding fallacies misrepresenting scientific publications in evidence
M Glockner, Y Hou, P Nakov, I Gurevych
arXiv preprint arXiv:2408.12812, 2024
32024
Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
J Yang, M Glockner, A Rocha, I Gurevych
arXiv preprint arXiv:2502.04797, 2025
2025
Breaking NLI Systems
M Glockner, V Shwartz, Y Goldberg
2018
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–9