大模型
arxiv.org ·
相同文本，不同数字：基于 LLM 的测量指标的分歧
该论文考察 LLM 文本测量对模型选择的敏感性：用 7 个不同厂商的 LLM 对 S&P 500 财报电话会议记录计算 13 个指标（情感、管理层清晰度、不确定性、回答具体性、气候与政治风险等）。结果显示跨模型排名相关性平均仅 0.52，转录本层面跨厂商共同差异仅占总分数变异的 34%；跨模型分歧无法预测后续分析师或市场分歧，提示存在显著的模型特异成分而非底层披露的共同模糊性。模型选择会显著改变下游推断的系数大小、符号与统计显著性；跨厂商平均可提升多数构念的排名稳定性，但分数水平仍受纳入模型影响。作者建议将 LLM 生成变量视为模型依赖的测量并跨厂商验证。
AI推荐理由 arXiv 论文，方法明确：用 7 个不同厂商的 LLM 对 S&P 500 财报电话会议记录按 13 个文本指标（情感、管理层清晰度、不确定性、回答具体性、气候与政治风险等）打分，发现跨模型排名相关性平均仅 0.52，且转录本层面跨厂商共同差异只占总分数变异的 34%；跨模型分歧不能预测后续分析师或市场分歧，说明存在显著的模型特异成分；模型选择会显著影响下游回归系数的量级、符号与显著性；跨厂商平均可提高多数构念的排名稳定性，但分数水平仍对纳入哪些模型敏感。结论是 LLM 生成的变量应视为模型依赖的测量并跨厂商验证。对使用 LLM 做文本量化研究、金融 NLP 与评测的开发者有直接方法论价值，局限是仅覆盖财报电话会议这一语料与 13 个构念，未给出跨领域外推证据。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.31013 (cs)
[Submitted on 25 Sep 2026]
Title:Same Text, Different Numbers: The Divergence of LLM-Based Measures
Authors:Hamid Boustanifar, Sasan Mansouri
View a PDF of the paper titled Same Text, Different Numbers: The Divergence of LLM-Based Measures, by Hamid Boustanifar and 1 other authors
View PDF
HTML (experimental)
Abstract:Researchers increasingly use generative large language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which LLM-based textual measures are invariant to model choice using thirteen measures, including sentiment, management clarity, uncertainty, answer specificity, and climate and political risk. Seven LLMs from different providers score earnings call transcripts of S&P 500 companies on these constructs. Cross-model rank correlations average only 0.52, and transcript-level differences common across providers account for only 34% of total score variation. Cross-model disagreement does not predict subsequent analyst or market disagreement, consistent with a substantial model-specific component rather than common ambiguity in the underlying disclosure. Model choice significantly affects downstream inference, with coefficient magnitudes, signs, and statistical significance varying substantially across models. Averaging across providers makes transcript rankings more stable for most constructs, but score levels remain sensitive to the models included in the ensemble. LLM-generated variables should therefore be treated as model-contingent measurements and validated across providers.
Comments:
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); General Finance (q-fin.GN); Risk Management (q-fin.RM)
Cite as:
arXiv:2609.31013 [cs.AI]
(or
arXiv:2609.31013v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.31013
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Sasan Mansouri [view email]
[v1]
Fri, 25 Sep 2026 09:04:10 UTC (6,962 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Same Text, Different Numbers: The Divergence of LLM-Based Measures, by Hamid Boustanifar and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
q-fin
q-fin.GN
q-fin.RM
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)