Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
Sungho Ko, Hyunjin Cho, Hyungjoo Chae, Jinyoung Yeo, Dongha Lee
Abstract
Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challenging. Existing methods, like concatenation or free-form textual conversion of triples, have limitations, including duplicated entities or relations, reduced evidence density, and failure to highlight crucial evidence. To address these issues, we propose EFSum, an Evidence-focused Fact Summarization framework for enhanced QA with knowledge-augmented LLMs. We optimize an LLM as a fact summarizer through distillation and preference alignment. Our extensive expeirments show that EFSum improves LLM’s zero-shot QA performance with its helpful and faithful summaries, especially when noisy facts are retrieved.
BibTeX
@inproceedings{ko-etal-2024-evidence,
title = "Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering",
author = "Ko, Sungho and
Cho, Hyunjin and
Chae, Hyungjoo and
Yeo, Jinyoung and
Lee, Dongha",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.594/",
doi = "10.18653/v1/2024.emnlp-main.594",
pages = "10636--10651"
}