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

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

Authors: Anderson Morillo, Edwin Puertas, Juan Carlos Martinez Santos

Venue: Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), Vienna, Austria. Association for Computational Linguistics. Pages 1534–1541.

Anthology ID: 2025.semeval-1.202 (no separate DOI assigned in the ACL Anthology record)

Links: PDF · ACL Anthology

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.