Theoretical and Empirical Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Open-World ScenariosPaulo Rodrigo CavalinClaudio Santos Pinhanez2024LREC-COLING 2024
Prompting-based Synthetic Data Generation for Few-Shot Question AnsweringMaximilian SchmidtAndrea Bartezzaghiet al.2024LREC-COLING 2024
Automatic Manipulation of Training Corpora to Make Parsers Accept Real-world TextHiroshi KanayamaRan Iwamotoet al.2024LREC-COLING 2024
Deductive Verification of LLM generated SPARQL queriesAlexandre RademakerGuilherme Augusto Ferreira Limaet al.2024LREC-COLING 2024
Quantifying the Ethical Dilemma of Using Culturally Toxic Training Data in AI Tools for Indigenous LanguagesPedro DominguesClaudio Santos Pinhanezet al.2024LREC-COLING 2024
Navigating the Modern Evaluation Landscape: Considerations in Benchmarks and Frameworks for Large Language Models (LLMs)Leshem ChoshenAriel Geraet al.2024LREC-COLING 2024