Real-World Summarization: When Evaluation Reaches Its Limits
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511650" target="_blank" >RIV/00216208:11320/25:10511650 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2025.findings-emnlp.1363/" target="_blank" >https://aclanthology.org/2025.findings-emnlp.1363/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Real-World Summarization: When Evaluation Reaches Its Limits
Original language description
We examine evaluation of faithfulness to input data in the context of hotel highlights-brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment and span-level annotation, we compare traditional metrics, trainable methods, and LLM-as-a-judge approaches. Our findings reveal that simpler metrics like word overlap correlate surprisingly well with human judgments (r=0.63), often outperforming more complex methods when applied to outof- domain data. We further demonstrate that while LLMs can generate high-quality highlights, they prove unreliable for evaluation as they tend to severely under- or over-annotate. Our analysis of real-world business impacts shows incorrect and non-checkable information pose the greatest risks. We also highlight challenges in crowdsourced evaluations.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Findings of the Association for Computational Linguistics: EMNLP 2025
ISBN
979-8-89176-335-7
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
25014-25026
Publisher name
Association for Computational Linguistics
Place of publication
Kerrville, TX, USA
Event location
Suzhou, China
Event date
Nov 4, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—