arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03033cs.CLcs.CE
收藏

L3iTC 参加 FinLLM 挑战赛任务:面向金融文本分类与摘要的量化方法

L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization

Trading Central Labs, Trading Central(Trading Central Labs、Trading Central);University of La Rochelle(拉罗谢尔大学)

Elvys Linhares Pontes, Carlos-Emiliano González-Gallardo, Mohamed Benjannet, Caryn Qu, Antoine Doucet

AI总结:

本文提出结合 4-bit 量化与 LoRA 微调大语言模型,在低 GPU 显存下高效完成金融文本分类与摘要任务,并在 FinLLM 2024 挑战赛中分别取得第三名和第六名。

摘要:

本文详细介绍了我们(L3iTC)参加 2024 年 FinLLM 挑战赛任务的情况,重点关注两个关键领域:任务 1,金融文本分类,以及任务 2,金融文本摘要。为应对这些挑战,我们微调了多个大语言模型(LLMs),以优化每个任务的性能。具体来说,我们使用了 4-bit 量化和 LoRA 来确定 LLMs 中哪些层应以较低精度进行训练。该方法不仅加速了在主办方提供的训练数据上的微调过程,还使我们能够在较低的 GPU 显存条件下运行模型。我们微调后的模型在金融分类任务中以 0.7543 的 F1-score 获得第三名,并在官方测试数据集上的金融摘要任务中获得第六名。

英文摘要:

This article details our participation (L3iTC) in the FinLLM Challenge Task 2024, focusing on two key areas: Task 1, financial text classification, and Task 2, financial text summarization. To address these challenges, we fine-tuned several large language models (LLMs) to optimize performance for each task. Specifically, we used 4-bit quantization and LoRA to determine which layers of the LLMs should be trained at a lower precision. This approach not only accelerated the fine-tuning process on the training data provided by the organizers but also enabled us to run the models on low GPU memory. Our fine-tuned models achieved third place for the financial classification task with an F1-score of 0.7543 and secured sixth place in the financial summarization task on the official test datasets.

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。

↑