TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911031678205952 |
|---|---|
| author | Anschütz, Miriam Gikalo, Ekaterina Herbster, Niklas Groh, Georg |
| author_facet | Anschütz, Miriam Gikalo, Ekaterina Herbster, Niklas Groh, Georg |
| contents | Hallucinations are one of the major problems of LLMs, hindering their trustworthiness and deployment to wider use cases. However, most of the research on hallucinations focuses on English data, neglecting the multilingual nature of LLMs. This paper describes our submission to the SemEval-2025 Task-3 - Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. We propose a two-part pipeline that combines retrieval-based fact verification against Wikipedia with a BERT-based system fine-tuned to identify common hallucination patterns. Our system achieves competitive results across all languages, reaching top-10 results in eight languages, including English. Moreover, it supports multiple languages beyond the fourteen covered by the shared task. This multilingual hallucination identifier can help to improve LLM outputs and their usefulness in the future. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification Anschütz, Miriam Gikalo, Ekaterina Herbster, Niklas Groh, Georg Computation and Language Artificial Intelligence Hallucinations are one of the major problems of LLMs, hindering their trustworthiness and deployment to wider use cases. However, most of the research on hallucinations focuses on English data, neglecting the multilingual nature of LLMs. This paper describes our submission to the SemEval-2025 Task-3 - Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. We propose a two-part pipeline that combines retrieval-based fact verification against Wikipedia with a BERT-based system fine-tuned to identify common hallucination patterns. Our system achieves competitive results across all languages, reaching top-10 results in eight languages, including English. Moreover, it supports multiple languages beyond the fourteen covered by the shared task. This multilingual hallucination identifier can help to improve LLM outputs and their usefulness in the future. |
| title | TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.00579 |