@inproceedings{fons-etal-2026-systematic,
title = "Systematic Multi-Aspect Evaluation of Time Series-Based Report Generation: The Case of Financial Analysis from Stock Data",
author = "Fons, Elizabeth and
Kochkina, Elena and
Kaur, Rachneet and
Zeng, Zhen and
Hlavaty, Berowne and
Smiley, Charese and
Vyetrenko, Svitlana and
Veloso, Manuela",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.305/",
doi = "10.63317/2u7a679u9rkq",
pages = "3833--3850",
abstract = "This paper explores the capability of large language models (LLMs) to generate coherent textual reports from time series data, using financial reports from stock data as the use case. We conduct a comprehensive multi-aspect evaluation across four model families, including linguistic quality, content source attribution, automated metrics, and expert human assessment. We evaluate models using four major stock indices and two synthetic time series to assess generalization. We assess reports based on single and multiple time series data, and experiment with plain text and multi-modal prompting. We examine temporal effects by analyzing report quality as data approaches model knowledge cutoffs and testing synthetic future intervals. Our evaluation shows that LLMs are capable of creating high-quality financial analyst reports, with larger models demonstrating superior performance, however even those require human oversight and have potential for temporal logic errors. Our findings reveal model-specific behavioral patterns that enable tailored generation pipelines and inform future research about model pitfalls in time series-to-text generation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fons-etal-2026-systematic">
<titleInfo>
<title>Systematic Multi-Aspect Evaluation of Time Series-Based Report Generation: The Case of Financial Analysis from Stock Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Fons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Kochkina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachneet</namePart>
<namePart type="family">Kaur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berowne</namePart>
<namePart type="family">Hlavaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charese</namePart>
<namePart type="family">Smiley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svitlana</namePart>
<namePart type="family">Vyetrenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuela</namePart>
<namePart type="family">Veloso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the capability of large language models (LLMs) to generate coherent textual reports from time series data, using financial reports from stock data as the use case. We conduct a comprehensive multi-aspect evaluation across four model families, including linguistic quality, content source attribution, automated metrics, and expert human assessment. We evaluate models using four major stock indices and two synthetic time series to assess generalization. We assess reports based on single and multiple time series data, and experiment with plain text and multi-modal prompting. We examine temporal effects by analyzing report quality as data approaches model knowledge cutoffs and testing synthetic future intervals. Our evaluation shows that LLMs are capable of creating high-quality financial analyst reports, with larger models demonstrating superior performance, however even those require human oversight and have potential for temporal logic errors. Our findings reveal model-specific behavioral patterns that enable tailored generation pipelines and inform future research about model pitfalls in time series-to-text generation tasks.</abstract>
<identifier type="citekey">fons-etal-2026-systematic</identifier>
<identifier type="doi">10.63317/2u7a679u9rkq</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.305/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3833</start>
<end>3850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Systematic Multi-Aspect Evaluation of Time Series-Based Report Generation: The Case of Financial Analysis from Stock Data
%A Fons, Elizabeth
%A Kochkina, Elena
%A Kaur, Rachneet
%A Zeng, Zhen
%A Hlavaty, Berowne
%A Smiley, Charese
%A Vyetrenko, Svitlana
%A Veloso, Manuela
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F fons-etal-2026-systematic
%X This paper explores the capability of large language models (LLMs) to generate coherent textual reports from time series data, using financial reports from stock data as the use case. We conduct a comprehensive multi-aspect evaluation across four model families, including linguistic quality, content source attribution, automated metrics, and expert human assessment. We evaluate models using four major stock indices and two synthetic time series to assess generalization. We assess reports based on single and multiple time series data, and experiment with plain text and multi-modal prompting. We examine temporal effects by analyzing report quality as data approaches model knowledge cutoffs and testing synthetic future intervals. Our evaluation shows that LLMs are capable of creating high-quality financial analyst reports, with larger models demonstrating superior performance, however even those require human oversight and have potential for temporal logic errors. Our findings reveal model-specific behavioral patterns that enable tailored generation pipelines and inform future research about model pitfalls in time series-to-text generation tasks.
%R 10.63317/2u7a679u9rkq
%U https://aclanthology.org/2026.lrec-1.305/
%U https://doi.org/10.63317/2u7a679u9rkq
%P 3833-3850
Markdown (Informal)
[Systematic Multi-Aspect Evaluation of Time Series-Based Report Generation: The Case of Financial Analysis from Stock Data](https://aclanthology.org/2026.lrec-1.305/) (Fons et al., LREC 2026)
ACL
- Elizabeth Fons, Elena Kochkina, Rachneet Kaur, Zhen Zeng, Berowne Hlavaty, Charese Smiley, Svitlana Vyetrenko, and Manuela Veloso. 2026. Systematic Multi-Aspect Evaluation of Time Series-Based Report Generation: The Case of Financial Analysis from Stock Data. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3833–3850, Palma de Mallorca, Spain. ELRA Language Resource Association.