Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iravani, Sahar, Conrad, Tim . O . F
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917805971996672
author Iravani, Sahar
Conrad, Tim . O . F
author_facet Iravani, Sahar
Conrad, Tim . O . F
contents Table processing, a key task in natural language processing, has significantly benefited from recent advancements in language models (LMs). However, the capabilities of LMs in table-to-text generation, which transforms structured data into coherent narrative text, require an in-depth investigation, especially with current open-source models. This study explores the effectiveness of various in-context learning strategies in LMs across benchmark datasets, focusing on the impact of providing examples to the model. More importantly, we examine a real-world use case, offering valuable insights into practical applications. To complement traditional evaluation metrics, we employ a large language model (LLM) self-evaluation approach using chain-of-thought reasoning and assess its correlation with human-aligned metrics like BERTScore. Our findings highlight the significant impact of examples in improving table-to-text generation and suggest that, while LLM self-evaluation has potential, its current alignment with human judgment could be enhanced. This points to the need for more reliable evaluation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12878
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models
Iravani, Sahar
Conrad, Tim . O . F
Computation and Language
Artificial Intelligence
Machine Learning
Table processing, a key task in natural language processing, has significantly benefited from recent advancements in language models (LMs). However, the capabilities of LMs in table-to-text generation, which transforms structured data into coherent narrative text, require an in-depth investigation, especially with current open-source models. This study explores the effectiveness of various in-context learning strategies in LMs across benchmark datasets, focusing on the impact of providing examples to the model. More importantly, we examine a real-world use case, offering valuable insights into practical applications. To complement traditional evaluation metrics, we employ a large language model (LLM) self-evaluation approach using chain-of-thought reasoning and assess its correlation with human-aligned metrics like BERTScore. Our findings highlight the significant impact of examples in improving table-to-text generation and suggest that, while LLM self-evaluation has potential, its current alignment with human judgment could be enhanced. This points to the need for more reliable evaluation methods.
title Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.12878