arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.20965q-fin.TRcs.AIcs.MAq-fin.CPq-fin.ST
收藏

学习聚合零样本大语言模型代理以进行企业披露分类

Learning to Aggregate Zero-Shot LLM Agents for Corporate Disclosure Classification

University College London(伦敦大学学院)

Kemal Kirtac

AI总结:

本文通过聚合零样本大语言模型输出提升企业披露分类性能,发现监督聚合优于零样本投票,尤其在混合信号披露中表现更优。

摘要:

本文研究是否可以使用轻量级监督聚合器将多样化的零样本大语言模型输出整合为更强的企业披露分类信号。零样本LLM可以在无需任务特定微调的情况下读取披露,但其预测在提示视角、模型家族和置信度水平上往往变化较大。本文通过多提示框架,三个固定零样本LLM分类器从不同财务视角读取每份披露,并输出情感标签、置信度评分和简短解释。逻辑元分类器随后聚合这些输出以预测次日股票回报方向。为减少预训练模型污染,本文限制评估范围为9,860份美国企业披露,这些披露由大型上市公司在2025年1月至2026年3月间发布,且在冻结基础LLM发布后。结果显示,训练的聚合器优于单一分类器、多数投票、置信度加权投票、零样本LLM判断者和FinBERT基线。平衡准确率从最佳单一分类器的0.566提升至训练的聚合器的0.606。增益在混合信号披露中最大,其中分类器意见不一致。结果表明,零样本LLM输出包含互补的财务信号,同时显示最强增益来自监督聚合而非零样本投票本身。

英文摘要:

This paper studies whether a lightweight supervised aggregator can combine diverse zero-shot large language model outputs into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without task-specific fine-tuning, but their predictions often vary across prompt perspectives, model families, and confidence levels. I examine this problem with a multi-prompt framework in which three fixed zero-shot LLM classifiers read each disclosure from different financial perspectives and output a sentiment label, a confidence score, and a short rationale. A logistic meta-classifier then aggregates these outputs to predict next-day stock return direction. To reduce pretrained-model contamination, I restrict evaluation to a post-release sample of 9{,}860 U.S.\ corporate disclosures issued by large publicly traded firms between January 2025 and March 2026, after the release of the frozen base LLMs used in the experiment. Results show that the trained aggregator outperforms single classifiers, majority vote, confidence-weighted voting, a zero-shot LLM judge, and a FinBERT baseline. Balanced accuracy rises from 0.566 for the best single classifier to 0.606 for the trained aggregator. The gain is largest in mixed-signal disclosures where classifiers disagree. The results suggest that zero-shot LLM outputs contain complementary financial signals, while also showing that the strongest gains come from supervised aggregation rather than from zero-shot voting alone.

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。

↑