An Entity Linking Agent for Question Answering

TL;DR

This paper introduces an entity linking agent for question answering that leverages a Large Language Model to improve linking accuracy in short, ambiguous questions, demonstrating robustness through experimental validation.

Contribution

The paper presents a novel entity linking agent based on a Large Language Model that mimics human cognition for better performance in QA tasks.

Findings

The agent effectively identifies entity mentions in short questions.

It retrieves relevant candidate entities with high accuracy.

Experimental results confirm robustness and effectiveness.

Abstract

Some Question Answering (QA) systems rely on knowledge bases (KBs) to provide accurate answers. Entity Linking (EL) plays a critical role in linking natural language mentions to KB entries. However, most existing EL methods are designed for long contexts and do not perform well on short, ambiguous user questions in QA tasks. We propose an entity linking agent for QA, based on a Large Language Model that simulates human cognitive workflows. The agent actively identifies entity mentions, retrieves candidate entities, and makes decision. To verify the effectiveness of our agent, we conduct two experiments: tool-based entity linking and QA task evaluation. The results confirm the robustness and effectiveness of our agent.