Abstract
Generating natural language descriptions from structured tabular data is a crucial challenge with high-impact applications across diverse domains, including business intelligence, scientific communication, and data analytics. Traditional rule-based and machine learning approaches have faced limitations in reusability, vocabulary coverage, and handling complex table layouts. Recent advances in LLMs pre-trained on vast corpora offer an opportunity to overcome these limitations by leveraging their strong language understanding and generation capabilities in a flexible learning setup. In this paper, We conduct a comprehensive evaluation of two LLMs - GPT-3.5 and LLaMa2-7B - on table-to-text generation across three diverse public datasets: WebNLG, NumericNLG, and ToTTo. Our experiments investigate both zero-shot prompting techniques and finetuning using the parameter-efficient LoRA method. Results demonstrate GPT-3.5’s impressive capabilities, outperforming LLaMa2 in zero-shot settings. However, finetuning LLaMa2 on a subset of data significantly bridges this performance gap and produces generations much closer to ground truth and comparable to SOTA approaches. Our findings highlight LLMs’ promising potential for data-to-text while identifying key areas for future research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
An, C., Feng, J., Lv, K., Kong, L., Qiu, X., Huang, X.: CONT: contrastive neural text generation (2023)
Aribandi, V., et al.: Ext5: towards extreme multi-task scaling for transfer learning (2022)
Castro Ferreira, T., et al.: The 2020 bilingual, bi-directional WebNLG+ shared task: overview and evaluation results (WebNLG+ 2020). In: International Workshop on Natural Language Generation from the Semantic Web (WebNLG+), pp. 55–76. ACL (2020)
Chen, M., et al.: Towards table-to-text generation with pretrained language model: a table structure understanding and text deliberating approach (2023)
Chen, W.: Large language models are few (1)-shot table reasoners. In: Findings of the Association for Computational Linguistics: EACL, pp. 1120–1130. ACL (2023)
Chowdhery, A., et al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1–113 (2023)
Clive, J., Cao, K., Rei, M.: Control prefixes for parameter-efficient text generation. In: Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pp. 363–382. ACL (2022)
Gardent, C., Shimorina, A., Narayan, S., Perez-Beltrachini, L.: Creating training corpora for NLG micro-planners. In: ACL, pp. 179–188. ACL (2017)
Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)
Parikh, A., et al.: ToTTo: a controlled table-to-text generation dataset. In: EMNLP, pp. 1173–1186. ACL (2020)
Su, Y., Vandyke, D., Wang, S., Fang, Y., Collier, N.: Plan-then-generate: controlled data-to-text generation via planning (2021)
Suadaa, L.H., Kamigaito, H., Funakoshi, K., Okumura, M., Takamura, H.: Towards table-to-text generation with numerical reasoning. In: ACL and IJCNLP, pp. 1451–1465. ACL (2021)
Xu, L., Xie, H., Qin, S.Z.J., Tao, X., Wang, F.L.: Parameter-efficient fine-tuning methods for pretrained language models: a critical review and assessment (2023)
Acknowledgments
This work was partly supported by project FAIR - Future AI Research (PE00000013), under the NRRP MUR program funded by the EU-NGEU.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Oro, E., De Grandis, L., Granata, F.M., Ruffolo, M. (2024). Leveraging Large Language Models for Flexible and Robust Table-to-Text Generation. In: Strauss, C., Amagasa, T., Manco, G., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2024. Lecture Notes in Computer Science, vol 14910. Springer, Cham. https://doi.org/10.1007/978-3-031-68309-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-68309-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-68308-4
Online ISBN: 978-3-031-68309-1
eBook Packages: Computer ScienceComputer Science (R0)