VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations
Anderson Morillo, Edwin Puertas, Juan Carlos Martinez Santos
Abstract
Thefirst approach leverages advanced LLMs, employing a chain-of-thought prompting strategywith one-shot learning and Google snippets forcontext retrieval, demonstrating superior performance. The second approach utilizes traditional NLP analysis techniques, including semantic ranking, token-level extraction, and rigorous data cleaning, to identify hallucinations- Anthology ID:
- 2025.semeval-1.202
- Volume:
- Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
- Month:
- July
- Year:
- 2025
- Address:
- Vienna, Austria
- Editors:
- Sara Rosenthal, Aiala Rosá, Debanjan Ghosh, Marcos Zampieri
- Venues:
- SemEval | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1534–1541
- Language:
- URL:
- https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.202/
- DOI:
- Cite (ACL):
- Anderson Morillo, Edwin Puertas, and Juan Carlos Martinez Santos. 2025. VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1534–1541, Vienna, Austria. Association for Computational Linguistics.
- Cite (Informal):
- VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations (Morillo et al., SemEval 2025)
- PDF:
- https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.202.pdf