NCL-UoR 在 SemEval-2025 任务 3 中的表现：使用改进的 RefChecker 和改进的 SelfCheckGPT 检测多语言幻觉及相关可观察过度生成文本片段
NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT
AI总结：
针对 SemEval-2025 Mu-SHROOM 的多语言幻觉及文本片段定位任务，提出改进的 RefChecker 与 SelfCheckGPT，通过声明式事实验证、外部知识和增强提示实现有效检测。
摘要：
SemEval-2025 任务 3（Mu-SHROOM）专注于检测多种大型语言模型（LLM）在跨多种语言生成内容中的幻觉。该任务不仅要求识别幻觉是否存在，还要求准确定位其具体出现位置。为应对这一挑战，本研究提出两种方法：改进的 RefChecker 和改进的 SelfCheckGPT。改进的 RefChecker 将基于提示的事实验证集成到 References 中，将其构建为基于声明的测试，而非单一的外部知识来源。改进的 SelfCheckGPT 引入外部知识，以克服其对内部知识的依赖。此外，两种方法的原始提示设计均得到增强，以识别 LLM 生成文本中的幻觉词汇。实验结果证明了该方法的有效性：在测试数据集上跨多种语言检测幻觉取得较高排名，平均 IoU 为 0.5310，平均 COR 为 0.5669。
英文摘要：
SemEval-2025 Task 3 (Mu-SHROOM) focuses on detecting hallucinations in content generated by various large language models (LLMs) across multiple languages. This task involves not only identifying the presence of hallucinations but also pinpointing their specific occurrences. To tackle this challenge, this study introduces two methods: modified RefChecker and modified SelfCheckGPT. The modified RefChecker integrates prompt-based factual verification into References, structuring them as claim-based tests rather than single external knowledge sources. The modified SelfCheckGPT incorporates external knowledge to overcome its reliance on internal knowledge. In addition, both methods' original prompt designs are enhanced to identify hallucinated words within LLM-generated texts. Experimental results demonstrate the effectiveness of the approach, achieving a high ranking on the test dataset in detecting hallucinations across various languages, with an average IoU of 0.5310 and an average COR of 0.5669.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
