Learning to Verify Summary Facts with Fine-Grained LLM Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oh, Jihwan, Choi, Jeonghwan, Kim, Nicole Hee-Yeon, Yun, Taewon, Song, Hwanjun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915063682564096
author Oh, Jihwan
Choi, Jeonghwan
Kim, Nicole Hee-Yeon
Yun, Taewon
Song, Hwanjun
author_facet Oh, Jihwan
Choi, Jeonghwan
Kim, Nicole Hee-Yeon
Yun, Taewon
Song, Hwanjun
contents Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of using human-labeled data. We introduce FineSumFact, a large-scale dataset containing fine-grained factual feedback on summaries. We employ 10 distinct LLMs for diverse summary generation and Llama-3-70B-Instruct for feedback. We utilize this dataset to fine-tune the lightweight open-source model Llama-3-8B-Instruct, optimizing resource efficiency while maintaining high performance. Our experimental results reveal that the model trained on extensive LLM-generated datasets surpasses that trained on smaller human-annotated datasets when evaluated using human-generated test sets. Fine-tuning fact verification models with LLM feedback can be more effective and cost-efficient than using human feedback. The dataset is available at https://github.com/DISL-Lab/FineSumFact.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Verify Summary Facts with Fine-Grained LLM Feedback
Oh, Jihwan
Choi, Jeonghwan
Kim, Nicole Hee-Yeon
Yun, Taewon
Song, Hwanjun
Computation and Language
Artificial Intelligence
Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of using human-labeled data. We introduce FineSumFact, a large-scale dataset containing fine-grained factual feedback on summaries. We employ 10 distinct LLMs for diverse summary generation and Llama-3-70B-Instruct for feedback. We utilize this dataset to fine-tune the lightweight open-source model Llama-3-8B-Instruct, optimizing resource efficiency while maintaining high performance. Our experimental results reveal that the model trained on extensive LLM-generated datasets surpasses that trained on smaller human-annotated datasets when evaluated using human-generated test sets. Fine-tuning fact verification models with LLM feedback can be more effective and cost-efficient than using human feedback. The dataset is available at https://github.com/DISL-Lab/FineSumFact.
title Learning to Verify Summary Facts with Fine-Grained LLM Feedback
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.10689