对比提示与微调模型，提升数字类事实验证准确性
ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
- 用指令微调大模型零样本提示，或通过LoRA高效微调模型
- 基于LLaMA+LoRA的模型在英文验证集表现优异，但测试集性能下降明显
- 证据筛选策略影响结果，需关注细粒度证据与模型泛化能力
本文介绍我们在CLEF 2025 CheckThat! 实验任务3中的系统方案，旨在利用检索到的证据验证数值与时间类陈述。我们探索两种互补方法：使用指令微调的大语言模型（LLMs）进行零样本提示，以及基于参数高效LoRA的监督微调。为提升证据质量，研究了多种选择策略，包括全文输入、基于BM25和MiniLM的top-k句子过滤。最佳模型为经LoRA微调的LLaMA，在英文验证集上表现良好，但在测试集上出现显著性能下降，凸显泛化挑战。结果表明，证据粒度与模型适配对鲁棒的数值事实验证至关重要。
原文摘要 · Abstract (English)
This paper presents our system for Task 3 of the CLEF 2025 CheckThat! Lab, which focuses on verifying numerical and temporal claims using retrieved evidence. We explore two complementary approaches: zero-shot prompting with instruction-tuned large language models (LLMs) and supervised fine-tuning using parameter-efficient LoRA. To enhance evidence quality, we investigate several selection strategies, including full-document input and top-k sentence filtering using BM25 and MiniLM. Our best-performing model LLaMA fine-tuned with LoRA achieves strong performance on the English validation set. However, a notable drop in the test set highlights a generalization challenge. These findings underscore the importance of evidence granularity and model adaptation for robust numerical fact verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。