Tag
论文提出 MULTIFINGROUND 多语言金融基准，揭示语言模型虽能跨语言识别财务概念（准确率 97.3-99.4%），却在 26.6-41.9% 的情况下无法完整恢复对应的数值证据，凸显识别与证据落地之间的差距。
This paper introduces SANE, a lightweight plugin for retrieval-augmented generation that improves both retrieval and reading by selecting top candidates via synopses and performing blueprint-guided query-time evidence extraction.
This paper introduces the Nimblemind Multi-Agent System (nMAS) for extracting evidence of H. pylori infection from gastric biopsy reports, achieving 98.61% accuracy across 216 feature-case decisions and demonstrating substantial time savings over manual review.
This paper introduces SEEK, a framework for semantic evidence extraction in multilingual fact verification, which constructs coherent evidence chunks from full articles and fine-tunes multilingual LLMs with LoRA, achieving up to 20% improvement in macro-F1 over baselines.
This paper introduces PrimeFacts, a methodology and resource for extracting fine-grained evidence from fact-checking articles using large language models. The extracted premises improve evidence retrieval and claim verification performance by up to 30% in MRR and 10-20 points in Macro-F1.