用大模型零样本+微调检测金融虚假信息，无需外部证据也能准确识别。
Fact4ac at the Financial Misinformation Detection Challenge Task: Reference-Free Financial Misinformation Detection via Fine-Tuning and Few-Shot Prompting of Large Language Models
- 结合少样本提示与低秩微调，提升模型对金融语义的敏感度。
- 在公开和私有测试集上分别达到95.4%和96.3%的准确率。
- 适合需要无参考环境下的金融舆情监控与风险预警场景。
金融虚假信息泛滥严重威胁市场稳定与投资者信任，误导市场行为并引发关键信息不对称。在真实场景中，外部证据或辅助参考常不可得，使得此类信息的检测极具挑战。本文提出在RFC-BENCH框架下针对“无参考金融虚假信息检测”任务的胜出方法。该任务要求模型仅依赖内部语义理解与上下文一致性判断金融声明真伪，而非外部事实核验。为此，我们构建了一个整合上下文学习（零样本与少样本提示）与参数高效微调（LoRA）的综合框架，充分挖掘前沿大模型的推理能力，使其精准捕捉金融操纵中的细微语言线索。实验表明，所提系统在官方排行榜上表现卓越，于公开测试集达95.4%准确率，私有测试集达96.3%，验证了方法的鲁棒性，推动了金融自然语言处理中上下文感知虚假信息检测的发展。14B与32B规模模型已开源至HuggingFace。
原文摘要 · Abstract (English)
The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating critical information asymmetry. Detecting such misleading narratives is inherently challenging, particularly in real-world scenarios where external evidence or supplementary references for cross-verification are strictly unavailable. This paper presents our winning methodology for the "Reference-Free Financial Misinformation Detection" shared task. Built upon the recently proposed RFC-BENCH framework (Jiang et al. 2026), this task challenges models to determine the veracity of financial claims by relying solely on internal semantic understanding and contextual consistency, rather than external fact-checking. To address this formidable evaluation setup, we propose a comprehensive framework that capitalizes on the reasoning capabilities of state-of-the-art Large Language Models (LLMs). Our approach systematically integrates in-context learning, specifically zero-shot and few-shot prompting strategies, with Parameter-Efficient Fine-Tuning (PEFT) via Low-Rank Adaptation (LoRA) to optimally align the models with the subtle linguistic cues of financial manipulation. Our proposed system demonstrated superior efficacy, successfully securing the first-place ranking on both official leaderboards. Specifically, we achieved an accuracy of 95.4% on the public test set and 96.3% on the private test set, highlighting the robustness of our method and contributing to the acceleration of context-aware misinformation detection in financial Natural Language Processing. Our models (14B and 32B) are available at https://huggingface.co/KaiNKaiho.
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。