arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.15040cs.CL
收藏

基于GPT-4的隐式规则学习ESG分类

ESG Classification by Implicit Rule Learning via GPT-4

MODULABS;Chung-ang University(中央大学);Konkuk University(建国大学);Seoul Women's University(首尔女子大学);Yonsei University(延世大学)

Hyo Jeong Yun, Chanyoung Kim, Moonjeong Hahm, Kyuri Kim, Guijin Son

AI总结:

本文研究通过提示、思维链和动态上下文学习等策略引导GPT-4与未知ESG评估标准对齐,在韩语赛道任务中获第二名,揭示了语言模型在缺乏训练数据时处理金融任务的潜力。

摘要:

环境、社会和治理(ESG)因素被广泛采用作为更高的投资回报指标。因此,人们不断努力利用语言模型自动化ESG评估,以从海量网络文本中轻松提取信号。然而,由于评级机构对其评估指标保密,最近的方法面临训练数据缺乏的问题。本文研究了是否可以通过提示、思维链推理和动态上下文学习等策略,引导像GPT-4这样的最先进语言模型与未知的ESG评估标准对齐。我们通过在Shared-Task ML-ESG-3 Impact Type韩语赛道中获得第二名,证明了这些方法的有效性,且未在提供的训练数据上更新模型。我们还探讨了调整提示如何影响语言模型处理金融任务的能力,利用了具有公开权重的较小模型。我们观察到,更长的通用预训练与金融下游任务性能的提升相关。我们的发现展示了语言模型在缺乏显式训练样本的情况下,驾驭复杂、主观评估指南的潜力,揭示了金融下游任务的无训练解决方案的机会。

英文摘要:

Environmental, social, and governance (ESG) factors are widely adopted as higher investment return indicators. Accordingly, ongoing efforts are being made to automate ESG evaluation with language models to extract signals from massive web text easily. However, recent approaches suffer from a lack of training data, as rating agencies keep their evaluation metrics confidential. This paper investigates whether state-of-the-art language models like GPT-4 can be guided to align with unknown ESG evaluation criteria through strategies such as prompting, chain-of-thought reasoning, and dynamic in-context learning. We demonstrate the efficacy of these approaches by ranking 2nd in the Shared-Task ML-ESG-3 Impact Type track for Korean without updating the model on the provided training data. We also explore how adjusting prompts impacts the ability of language models to address financial tasks leveraging smaller models with openly available weights. We observe longer general pre-training to correlate with enhanced performance in financial downstream tasks. Our findings showcase the potential of language models to navigate complex, subjective evaluation guidelines despite lacking explicit training examples, revealing opportunities for training-free solutions for financial downstream tasks.

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。

↑