Facts-and-Feelings: Capturing both Objectivity and Subjectivity in Table-to-Text Generation

TL;DR

This paper introduces the Ta2TS dataset for table-to-text generation that captures both objective data and subjective interpretations, analyzing model performance in generating accurate and nuanced descriptions.

Contribution

It presents the first dataset combining objectivity and subjectivity in table-to-text generation and compares fine-tuned models with large language models on this task.

Findings

Fine-tuned LMs perform close to prompted LLMs.

Models achieve 85.15% BERTScore and 26.28% Meteor score.

First comprehensive analysis of LLMs on subjective table-to-text generation.

Abstract

Table-to-text generation, a long-standing challenge in natural language generation, has remained unexplored through the lens of subjectivity. Subjectivity here encompasses the comprehension of information derived from the table that cannot be described solely by objective data. Given the absence of pre-existing datasets, we introduce the Ta2TS dataset with 3849 data instances. We perform the task of fine-tuning sequence-to-sequence models on the linearized tables and prompting on popular large language models. We analyze the results from a quantitative and qualitative perspective to ensure the capture of subjectivity and factual consistency. The analysis shows the fine-tuned LMs can perform close to the prompted LLMs. Both the models can capture the tabular data, generating texts with 85.15% BERTScore and 26.28% Meteor score. To the best of our knowledge, we provide the first-of-its-kind dataset on tables with multiple genres and subjectivity included and present the first comprehensive analysis and comparison of different LLM performances on this task.