An Entity Linking Agent for Question Answering
This addresses a bottleneck for QA systems relying on knowledge bases, but it appears incremental as it adapts existing LLM techniques to a specific task.
The paper tackles the problem of entity linking in question answering, where existing methods underperform on short, ambiguous questions, by proposing an agent based on a Large Language Model that simulates human cognitive workflows, and results confirm its robustness and effectiveness.
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.