SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
By: Raúl Vázquez , Timothee Mickus , Elaine Zosa and more
Potential Business Impact:
Finds when AI makes up wrong information.
We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs). Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The large number of submissions underscores the interest of the community in hallucination detection. We present the results of the participating systems and conduct an empirical analysis to identify key factors contributing to strong performance in this task. We also emphasize relevant current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans.
Similar Papers
UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output
Computation and Language
Finds fake facts in AI answers.
HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection
Computation and Language
Helps computers spot fake words they make.
NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT
Computation and Language
Finds fake facts in computer writing.