TUM-MiKaNi 在 SemEval-2025 任务 3:迈向多语言与知识感知的非事实性幻觉识别
TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification
AI总结:
本文针对 LLM 幻觉研究多集中于英语的问题,提出结合 Wikipedia 检索式事实核查与微调 BERT 的两部分流水线,在 SemEval-2025 Mu-SHROOM 多语言任务中于八种语言进入前十,并支持超出任务范围的更多语言。
摘要:
幻觉是大型语言模型(LLM)的主要问题之一,阻碍了其可信度和在更广泛用例中的部署。然而,大多数关于幻觉的研究集中在英语数据上,忽视了 LLM 的多语言特性。本文描述了我们对 SemEval-2025 任务 3——Mu-SHROOM(多语言幻觉及相关可观察过度生成错误共享任务)的提交。我们提出了一个两部分的流水线,将基于 Wikipedia 的检索式事实核查与经过微调的 BERT 系统相结合,以识别常见的幻觉模式。我们的系统在所有语言上都取得了有竞争力的结果,在包括英语在内的八种语言中进入前十名。此外,它还支持共享任务所涵盖的十四种语言之外的多种语言。这种多语言幻觉识别器有助于在未来改进 LLM 的输出及其有用性。
英文摘要:
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.
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。