Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915157437841408 |
|---|---|
| author | Mahapatra, Joy Roy, Soumyajit Garain, Utpal |
| author_facet | Mahapatra, Joy Roy, Soumyajit Garain, Utpal |
| contents | Monitoring factual inconsistency is essential for ensuring trustworthiness in data-to-text generation (D2T). While large language models (LLMs) have demonstrated exceptional performance across various D2T tasks, previous studies on scaling laws have primarily focused on generalization error through power law scaling to LLM size (i.e., the number of model parameters). However, no research has examined the impact of LLM size on factual inconsistency in D2T. In this paper, we investigate how factual inconsistency in D2T scales with LLM size by exploring two scaling laws: power law and exponential scaling. To rigorously evaluate and compare these scaling laws, we employ a statistical validation framework consisting of three key stages: predictive performance estimation, goodness-of-fit assessment, and comparative analysis. For a comprehensive empirical study, we analyze three popular LLM families across five D2T datasets, measuring factual inconsistency inversely using four state-of-the-art consistency metrics. Our findings, based on exhaustive empirical results and validated through our framework, reveal that, contrary to the widely assumed power law scaling, factual inconsistency in D2T follows an exponential scaling with LLM size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation Mahapatra, Joy Roy, Soumyajit Garain, Utpal Computation and Language Artificial Intelligence Machine Learning Monitoring factual inconsistency is essential for ensuring trustworthiness in data-to-text generation (D2T). While large language models (LLMs) have demonstrated exceptional performance across various D2T tasks, previous studies on scaling laws have primarily focused on generalization error through power law scaling to LLM size (i.e., the number of model parameters). However, no research has examined the impact of LLM size on factual inconsistency in D2T. In this paper, we investigate how factual inconsistency in D2T scales with LLM size by exploring two scaling laws: power law and exponential scaling. To rigorously evaluate and compare these scaling laws, we employ a statistical validation framework consisting of three key stages: predictive performance estimation, goodness-of-fit assessment, and comparative analysis. For a comprehensive empirical study, we analyze three popular LLM families across five D2T datasets, measuring factual inconsistency inversely using four state-of-the-art consistency metrics. Our findings, based on exhaustive empirical results and validated through our framework, reveal that, contrary to the widely assumed power law scaling, factual inconsistency in D2T follows an exponential scaling with LLM size. |
| title | Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.12372 |