UMUTeam at SemEval-2024 Task 6: Leveraging Zero-Shot Learning for Detecting Hallucinations and Related Observable Overgeneration Mistakes
Ronghao Pan, José Antonio García-díaz, Tomás Bernal-beltrán, Rafael Valencia-garcía
Abstract
In these working notes we describe the UMUTeam’s participation in SemEval-2024 shared task 6, which aims at detecting grammatically correct output of Natural Language Generation with incorrect semantic information in two different setups: model-aware and model-agnostic tracks. The task is consists of three subtasks with different model setups. Our approach is based on exploiting the zero-shot classification capability of the Large Language Models LLaMa-2, Tulu and Mistral, through prompt engineering. Our system ranked eighteenth in the model-aware setup with an accuracy of 78.4% and 29th in the model-agnostic setup with an accuracy of 76.9333%.- Anthology ID:
- 2024.semeval-1.98
- Volume:
- Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 675–681
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.98
- DOI:
- 10.18653/v1/2024.semeval-1.98
- Cite (ACL):
- Ronghao Pan, José Antonio García-díaz, Tomás Bernal-beltrán, and Rafael Valencia-garcía. 2024. UMUTeam at SemEval-2024 Task 6: Leveraging Zero-Shot Learning for Detecting Hallucinations and Related Observable Overgeneration Mistakes. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 675–681, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- UMUTeam at SemEval-2024 Task 6: Leveraging Zero-Shot Learning for Detecting Hallucinations and Related Observable Overgeneration Mistakes (Pan et al., SemEval 2024)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2024.semeval-1.98.pdf