ATLANTIS at SemEval-2025 Task 3: Detecting Hallucinated Text Spans in Question Answering
This addresses the problem of hallucinations in LLMs for QA systems, but it is incremental as it builds on existing methods for a specific competition task.
The paper tackled detecting hallucinated text spans in question answering systems by exploring methods with and without external context, achieving top rankings in Spanish and competitive placements in English and German.
This paper presents the contributions of the ATLANTIS team to SemEval-2025 Task 3, focusing on detecting hallucinated text spans in question answering systems. Large Language Models (LLMs) have significantly advanced Natural Language Generation (NLG) but remain susceptible to hallucinations, generating incorrect or misleading content. To address this, we explored methods both with and without external context, utilizing few-shot prompting with a LLM, token-level classification or LLM fine-tuned on synthetic data. Notably, our approaches achieved top rankings in Spanish and competitive placements in English and German. This work highlights the importance of integrating relevant context to mitigate hallucinations and demonstrate the potential of fine-tuned models and prompt engineering.