VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations

Jul 1, 2025·
Anderson Morillo
,
Edwin Puertas
,
Juan Carlos Martinez Santos
· 0 min read
Abstract
The first approach leverages advanced LLMs, employing a chain-of-thought prompting strategy with one-shot learning and Google snippets for context 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.
Type
Publication
In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
Natural Language Processing Large Language Models Fact Retrieval Hallucination Detection Context Filtering Google Snippets