This paper describes the DipInfo-UniTo system participating to the GEM shared task 2024. We participate only to the Data-to-Text (D2T) task. The DipInfo-UniTo system is based on Mistral (Jiang et al., 2023), a recent Large Language Model (LLM). Most LLMs are capable of generating high-quality text for D2T tasks but, crucially, they often fall short in terms of adequacy, and sometimes exhibit {``}hallucinations{''}. To mitigate this issue, we have implemented a generation pipeline that combines LLMs with techniques from the traditional Natural Language Generation (NLG) pipeline. In particular, we have a three step process SGA, consisting in (1) Splitting the original set of triples, (2) Generating verbalizations from the resulting split data units, (3) Aggregating the verbalizations produced in the previous step.
DipInfo-UniTo at the GEM'24 Data-to-Text Task: Augmenting LLMs with the Split-Generate-Aggregate Pipeline
Oliverio, Michael
Membro del Collaboration Group
;Balestrucci, Pier Felice
Membro del Collaboration Group
;Mazzei, Alessandro
Membro del Collaboration Group
;Basile, Valerio
Membro del Collaboration Group
2024-01-01
Abstract
This paper describes the DipInfo-UniTo system participating to the GEM shared task 2024. We participate only to the Data-to-Text (D2T) task. The DipInfo-UniTo system is based on Mistral (Jiang et al., 2023), a recent Large Language Model (LLM). Most LLMs are capable of generating high-quality text for D2T tasks but, crucially, they often fall short in terms of adequacy, and sometimes exhibit {``}hallucinations{''}. To mitigate this issue, we have implemented a generation pipeline that combines LLMs with techniques from the traditional Natural Language Generation (NLG) pipeline. In particular, we have a three step process SGA, consisting in (1) Splitting the original set of triples, (2) Generating verbalizations from the resulting split data units, (3) Aggregating the verbalizations produced in the previous step.File | Dimensione | Formato | |
---|---|---|---|
2024.inlg-genchal.6.pdf
Accesso aperto
Tipo di file:
PDF EDITORIALE
Dimensione
298.12 kB
Formato
Adobe PDF
|
298.12 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.