Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Xu, Chen, Guanyi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.11965
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908369104666624
author Liu, Xu
Chen, Guanyi
author_facet Liu, Xu
Chen, Guanyi
contents We present the system developed by the Central China Normal University (CCNU) team for the Mu-SHROOM shared task, which focuses on identifying hallucinations in question-answering systems across 14 different languages. Our approach leverages multiple Large Language Models (LLMs) with distinct areas of expertise, employing them in parallel to annotate hallucinations, effectively simulating a crowdsourcing annotation process. Furthermore, each LLM-based annotator integrates both internal and external knowledge related to the input during the annotation process. Using the open-source LLM DeepSeek-V3, our system achieves the top ranking (\#1) for Hindi data and secures a Top-5 position in seven other languages. In this paper, we also discuss unsuccessful approaches explored during our development process and share key insights gained from participating in this shared task.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11965
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation
Liu, Xu
Chen, Guanyi
Computation and Language
We present the system developed by the Central China Normal University (CCNU) team for the Mu-SHROOM shared task, which focuses on identifying hallucinations in question-answering systems across 14 different languages. Our approach leverages multiple Large Language Models (LLMs) with distinct areas of expertise, employing them in parallel to annotate hallucinations, effectively simulating a crowdsourcing annotation process. Furthermore, each LLM-based annotator integrates both internal and external knowledge related to the input during the annotation process. Using the open-source LLM DeepSeek-V3, our system achieves the top ranking (\#1) for Hindi data and secures a Top-5 position in seven other languages. In this paper, we also discuss unsuccessful approaches explored during our development process and share key insights gained from participating in this shared task.
title CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation
topic Computation and Language
url https://arxiv.org/abs/2505.11965