FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511640" target="_blank" >RIV/00216208:11320/25:10511640 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.inlg-main.7" target="_blank" >https://aclanthology.org/2025.inlg-main.7</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation

Popis výsledku v původním jazyce

Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is af- fected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the- fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contam- ination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experi- ment with German, Russian and French in addi- tion to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic met- rics, but this does not translate into LLM and human evaluations. Domain effects are visi- ble in all evaluations, showing that a domain- balanced benchmark is more challenging.

Název v anglickém jazyce

FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation

Popis výsledku anglicky

Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is af- fected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the- fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contam- ination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experi- ment with German, Russian and French in addi- tion to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic met- rics, but this does not translate into LLM and human evaluations. Domain effects are visi- ble in all evaluations, showing that a domain- balanced benchmark is more challenging.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 18th International Natural Language Generation Conference

ISBN

979-8-89176-321-0

ISSN

—

e-ISSN

—

Počet stran výsledku

14

Strana od-do

108-121

Název nakladatele

Association for Computational Linguistics

Místo vydání

Kerrville, TX, USA

Místo konání akce

Hanoi, Vietnam

Datum konání akce

29. 10. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—