Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ko, Sungho, Cho, Hyunjin, Chae, Hyungjoo, Yeo, Jinyoung, Lee, Dongha
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913536355074048
author Ko, Sungho
Cho, Hyunjin
Chae, Hyungjoo
Yeo, Jinyoung
Lee, Dongha
author_facet Ko, Sungho
Cho, Hyunjin
Chae, Hyungjoo
Yeo, Jinyoung
Lee, Dongha
contents Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challengin. Existing methods, such as triple-form or free-form textual conversion of triple-form facts, encounter several issues. These include reduced evidence density due to duplicated entities or relationships, and reduced evidence clarity due to an inability to emphasize 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 open-source LLM as a fact summarizer through distillation and preference alignment. Our extensive experiments show that EFSum improves LLM's zero-shot QA performance, and it is possible to ensure both the helpfulness and faithfulness of the summary.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02966
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
Ko, Sungho
Cho, Hyunjin
Chae, Hyungjoo
Yeo, Jinyoung
Lee, Dongha
Computation and Language
Artificial Intelligence
Machine Learning
Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challengin. Existing methods, such as triple-form or free-form textual conversion of triple-form facts, encounter several issues. These include reduced evidence density due to duplicated entities or relationships, and reduced evidence clarity due to an inability to emphasize 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 open-source LLM as a fact summarizer through distillation and preference alignment. Our extensive experiments show that EFSum improves LLM's zero-shot QA performance, and it is possible to ensure both the helpfulness and faithfulness of the summary.
title Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2403.02966