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

TL;DR

EFSum is a novel framework that improves zero-shot question answering by generating evidence-focused fact summaries from knowledge graphs, enhancing clarity and relevance for large language models.

Contribution

The paper introduces EFSum, a new fact summarization method that optimizes an open-source LLM for better evidence presentation in knowledge-augmented QA.

Findings

EFSum improves zero-shot QA performance of LLMs.

EFSum ensures helpfulness and faithfulness of summaries.

The method enhances evidence density and clarity in knowledge graph verbalization.

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 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.