English(EN) Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts

研究：LLM 金融预测受语气影响大于盈利

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

一项发表在 arXiv 上的新研究调查了影响语言模型金融预测的因素。研究人员构建了合成的盈利公告，以测试动量、评论语气和盈利惊喜对来自四个模型系列的六种不同的指令/聊天检查点转换的影响。研究结果表明，评论语气和动量对模型预测的影响通常大于实际每股收益的对比。 AI

影响这项研究突显了 LLM 金融预测中潜在的偏见，表明模型输出可能比事实数据对风格元素更敏感。

排序理由该集群包含一篇详细介绍 LLM 行为实验的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍 LLM 行为实验的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Alina Khaybullina · 2026-10-16 04:00

LLM 金融预测中的动量、评论基调和盈利惊喜

arXiv:2610.22043v1 Announce Type: cross Abstract: Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational commentary tone, and whether fixed actual EPS beats a manipulate…